{
  "fetched_at": "2026-10-24T22:33:41Z",
  "source_url": "https://www.kaggle.com/competitions/customer-flags-prediction-challenge/data",
  "pages": [
    {
      "name": "data-description",
      "content": "In the **Customer Flags Prediction Challenge**, participants are provided with three main datasets to build their predictive models. Each dataset contains crucial information that will help you understand customer behaviors and attributes. Below is a detailed description of each dataset, including file contents and how they relate to the competition objectives.\n\n---\n\n## **Dataset Overview**\n\n1. **Customer Features Data**\n   - **Filename**: `customer_features.zip`\n   - **Extracted File**: `customer_features.csv`\n   - **Description**: Contains detailed customer information, including demographic data, account creation details, activity timestamps, and target flags.\n\n2. **Balance Features Data**\n   - **Filename**: `customer_account_balances.zip`\n   - **Extracted File**: `balance_features.csv`\n   - **Description**: Provides information about customers' account balances across various currencies at specific timestamps.\n\n3. **Test Data**\n   - **Filename**: `test.zip`\n   - **Extracted File**: `test.csv`\n   - **Description**: Contains the test set for which you need to predict the target flags. It includes the same features as the training data but excludes the target variables.\n\n---\n\n## **1. Customer Features Data**\n\n### **File Information**\n\n- **Compressed File**: `customer_features.zip`\n- **Uncompressed File**: `customer_features.csv`\n- **File Format**: CSV (Comma-Separated Values)\n\n### **Description**\n\nThis dataset includes comprehensive information about each customer and serves as the primary source for feature extraction. It contains both input features and the target variables (except in the test set).\n\n### **Data Fields**\n\n1. **customer_id** *(string)*\n\n   - **Description**: Unique identifier for each customer.\n   - **Notes**: This field is the primary key and is used to link with other datasets.\n\n2. **sign_up_date** *(datetime)*\n\n   - **Description**: The date and time when the customer signed up on the platform.\n   - **Format**: YYYY-MM-DD HH:MM:SS\n\n3. **created_at** *(datetime)*\n\n   - **Description**: Timestamp indicating when the customer account was created.\n   - **Notes**: May be similar to `sign_up_date` but can differ in some cases.\n\n4. **first_trade_time** *(datetime)*\n\n   - **Description**: Timestamp of the customer's first trade activity.\n   - **Notes**: This field is sparse; many customers may not have initiated a trade.\n\n5. **first_offramp_time** *(datetime)*\n\n   - **Description**: Timestamp of the customer's first offramp activity (withdrawing funds from the platform).\n   - **Notes**: Sparse data; useful for understanding customer engagement.\n\n6. **first_onramp_time** *(datetime)*\n\n   - **Description**: Timestamp of the customer's first onramp activity (depositing funds into the platform).\n   - **Notes**: Sparse data; indicates initial engagement.\n\n7. **gender** *(string)*\n\n   - **Description**: Gender of the customer.\n   - **Possible Values**: 'Male', 'Female', 'Other', or may be missing.\n   - **Notes**: May contain missing or unspecified values.\n\n8. **dob** *(date)*\n\n   - **Description**: Date of birth of the customer.\n   - **Format**: YYYY-MM-DD\n   - **Notes**: May contain missing values.\n\n9. **banker_score** *(float)*\n\n   - **Description**: A score representing the customer's activity level or engagement on the platform.\n   - **Range**: [Insert range if known]\n   - **Notes**: The exact calculation method may be proprietary.\n\n10. **virtual_flag** *(int)*\n\n    - **Description**: **Target variable** indicating whether the customer account is virtual.\n    - **Values**: 1 (Virtual account), 0 (Real account)\n\n11. **system_flag** *(int)*\n\n    - **Description**: **Target variable** indicating whether the account is system-generated.\n    - **Values**: 1 (System-generated account), 0 (Not system-generated)\n\n12. **cloned_flag** *(int)*\n\n    - **Description**: **Target variable** indicating whether the account is cloned.\n    - **Values**: 1 (Cloned account), 0 (Not cloned)\n\n13. **seeder** *(int)*\n\n    - **Description**: **Target variable** indicating whether the customer is a seeder.\n    - **Values**: 1 (Seeder), 0 (Not a seeder)\n\n### **Usage Notes**\n\n- **Target Variables**: The four flags (`virtual_flag`, `system_flag`, `cloned_flag`, `seeder`) are the target variables you need to predict.\n- **Missing Data**: Some fields, such as `gender` and `dob`, may have missing values. Appropriate handling (e.g., imputation or modeling missingness) is necessary.\n- **Time-Based Features**: The timestamps can be used to create features like account age, time since last activity, etc.\n\n---\n\n## **2. Balance Features Data**\n\n### **File Information**\n\n- **Compressed File**: `customer_account_balances.zip`\n- **Uncompressed File**: `balance_features.csv`\n- **File Format**: CSV\n\n### **Description**\n\nThis dataset provides snapshots of customer account balances across different currencies. It can help in understanding customers' financial behaviors and engagement levels.\n\n### **Data Fields**\n\n1. **customer_id** *(string)*\n\n   - **Description**: Unique identifier linking to the `customer_features.csv`.\n   - **Notes**: Use this field to merge with customer features.\n\n2. **currency_code** *(int)*\n\n   - **Description**: Numeric code representing the type of currency (e.g., USD, EUR, cryptocurrency codes).\n   - **Notes**: A mapping of `currency_code` to actual currency names may be provided or inferred.\n\n3. **balance** *(float)*\n\n   - **Description**: The available balance for the customer in the specified currency.\n   - **Notes**: Represents funds that are available for transactions.\n\n4. **frozen_balance** *(float)*\n\n   - **Description**: The portion of the customer's balance that is frozen or on hold.\n   - **Notes**: Funds may be frozen due to holds, disputes, or regulatory reasons.\n\n5. **snapshot_timestamp** *(datetime)*\n\n   - **Description**: The date and time when the balance snapshot was taken.\n   - **Format**: YYYY-MM-DD HH:MM:SS\n   - **Notes**: If multiple snapshots are available, you can analyze balance trends over time.\n\n### **Usage Notes**\n\n- **Multiple Records per Customer**: Customers may have multiple records if they hold balances in different currencies or if multiple snapshots are provided.\n- **Data Aggregation**: You may need to aggregate balances per customer (e.g., total balance, number of currencies held).\n- **Currency Handling**: Consider normalizing balances across different currencies if necessary (e.g., converting to a base currency).\n\n---\n\n## **3. Test Data**\n\n### **File Information**\n\n- **Compressed File**: `test.zip`\n- **Uncompressed File**: `test.csv`\n- **File Format**: CSV\n\n### **Description**\n\nThe test dataset contains customer features for which you need to predict the target flags. This dataset has the same structure as `customer_features.csv` but excludes the target variables (`virtual_flag`, `system_flag`, `cloned_flag`, `seeder`).\n\n### **Data Fields**\n\n- All fields from the **Customer Features Data**, except the target variables.\n\n### **Usage Notes**\n\n- **Predictions Required**: For each `customer_id` in the test set, you need to predict all four target flags.\n- **Feature Consistency**: Ensure that any feature engineering or preprocessing steps applied to the training data are consistently applied to the test data.\n\n---\n\n## **Data Relationships**\n\n- **Linking Datasets**: Use `customer_id` to link records between `customer_features.csv`, `balance_features.csv`, and `test.csv`.\n- **Primary and Foreign Keys**: `customer_id` acts as the primary key in `customer_features.csv` and as a foreign key in `balance_features.csv`.\n\n---\n\n## **Data Access and Extraction**\n\n### **Downloading the Data**\n\n- All datasets are available for download from the competition's **\"Data\"** tab.\n- **Note**: You may need to agree to the competition rules or data usage terms before downloading.\n\n### **Extracting the Data**\n\n- The files are compressed in ZIP format.\n- Use standard tools to extract the CSV files:\n  - **Windows**: Right-click the ZIP file and select \"Extract All...\"\n  - **macOS**: Double-click the ZIP file to extract.\n  - **Linux**: Use the `unzip` command in the terminal.\n  - **Python**: Use the `zipfile` module to extract programmatically.\n\n### **Example in Python**\n\n```python\nimport zipfile\n\n# Extract customer_features.zip\nwith zipfile.ZipFile('customer_features.zip', 'r') as zip_ref:\n    zip_ref.extractall()\n\n# Extract customer_account_balances.zip\nwith zipfile.ZipFile('customer_account_balances.zip', 'r') as zip_ref:\n    zip_ref.extractall()\n\n# Extract test.zip\nwith zipfile.ZipFile('test.zip', 'r') as zip_ref:\n    zip_ref.extractall()\n```\n\n---\n\n## **Data Quality and Preprocessing**\n\n- **Missing Values**: Identify and handle missing values in features like `gender`, `dob`, and activity timestamps.\n- **Data Types**: Ensure that date and timestamp fields are correctly parsed as datetime objects.\n- **Anomalies**: Check for inconsistent or outlier values that may need to be addressed.\n- **Normalization**: Consider normalizing numerical features like `banker_score`, `balance`, and `frozen_balance`.\n\n---\n\n## **Feature Engineering Suggestions**\n\n- **Temporal Features**:\n  - Account age: Difference between `snapshot_timestamp` and `created_at`.\n  - Time since last activity: Calculate durations since `first_trade_time`, `first_onramp_time`, etc.\n- **Financial Features**:\n  - Total balance: Sum of balances across all currencies per customer.\n  - Balance ratios: Ratio of `frozen_balance` to `balance`.\n  - Currency diversity: Number of different currencies held by the customer.\n- **Activity Indicators**:\n  - Binary flags indicating whether a customer has engaged in trading, on-ramping, or off-ramping.\n- **Demographic Features**:\n  - Age: Calculate from `dob`.\n  - Gender encoding: Convert categorical `gender` into numerical values.\n\n---\n\n## **Important Notes**\n\n- **Privacy and Anonymization**: All data has been anonymized to protect customer privacy. Do not attempt to de-anonymize or infer personal identities.\n- **Data Usage**: The data provided is for the sole purpose of this competition. Do not distribute or use the data for other purposes.\n- **External Data**: The use of external data is prohibited. All features must be derived from the provided datasets.\n\n---\n\n## **Data Dictionary Summary**\n\n| Field Name           | Data Type | Description                                                  |\n|----------------------|-----------|--------------------------------------------------------------|\n| **customer_id**      | string    | Unique customer identifier                                   |\n| **sign_up_date**     | datetime  | Customer sign-up date and time                               |\n| **created_at**       | datetime  | Account creation timestamp                                   |\n| **first_trade_time** | datetime  | Timestamp of first trade activity                            |\n| **first_offramp_time** | datetime | Timestamp of first offramp activity                          |\n| **first_onramp_time** | datetime  | Timestamp of first onramp activity                           |\n| **gender**           | string    | Customer's gender                                            |\n| **dob**              | date      | Customer's date of birth                                     |\n| **banker_score**     | float     | Customer activity score                                      |\n| **virtual_flag**     | int       | Target: Virtual account flag (1 or 0)                        |\n| **system_flag**      | int       | Target: System-generated account flag (1 or 0)               |\n| **cloned_flag**      | int       | Target: Cloned account flag (1 or 0)                         |\n| **seeder**           | int       | Target: Seeder flag (1 or 0)                                 |\n| **currency_code**    | int       | Code representing currency type                              |\n| **balance**          | float     | Available balance in specified currency                      |\n| **frozen_balance**   | float     | Frozen balance in specified currency                         |\n| **snapshot_timestamp** | datetime | Timestamp when balance snapshot was taken                   |\n\n---\n\n## **Next Steps**\n\n- **Data Exploration**: Begin by exploring the datasets to understand distributions, correlations, and potential data quality issues.\n- **Feature Engineering**: Create meaningful features that could improve model performance.\n- **Model Development**: Develop and train models using the training data, and generate predictions for the test set.\n- **Submission**: Prepare your submission file as per the guidelines and submit it for evaluation.\n\n---\n\n## **Assistance and Resources**\n\n- **Discussion Forums**: Engage with the community to ask questions and share insights.\n- **Starter Notebook**: Utilize the provided starter notebook to kickstart your analysis.\n- **FAQs**: Check the FAQs for answers to common questions about the data.\n\n---\n\nBy thoroughly understanding the datasets and their nuances, you'll be better equipped to build effective models for the **Customer Flags Prediction Challenge**. Good luck, and we look forward to seeing your innovative approaches!\n\n---\n\n*Note: If you have specific questions about the datasets or encounter any issues, please reach out through the competition's **Discussion Forum** or contact the organizers directly.*",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "\n## **In-Depth Domain Explanation and Problem Exploration**\n\n### **Domain Context**\n\n#### **Industry Background**\n\nThe **Customer Flags Prediction Challenge** is set within the context of the **financial technology (FinTech)** industry, specifically focusing on digital financial platforms that offer services such as trading, on-ramping/off-ramping of funds, and account management. These platforms may include cryptocurrency exchanges, digital wallets, online brokerage services, or other financial service providers that operate digitally and handle a variety of currencies.\n\n#### **Business Operations**\n\nIn such platforms, understanding customer behavior and categorizing customer accounts accurately is critical for:\n\n- **Risk Management**: Identifying potential fraudulent activities and mitigating associated risks.\n- **Regulatory Compliance**: Ensuring adherence to financial regulations, including anti-money laundering (AML) and know your customer (KYC) requirements.\n- **Customer Service**: Tailoring services to meet the needs of different customer segments.\n- **Operational Efficiency**: Streamlining processes by automating the classification of accounts.\n\n---\n\n### **Deeper Dive into the Problem**\n\n#### **Understanding the Target Flags**\n\nThe four binary flags (`seeder`, `virtual_flag`, `system_flag`, `cloned_flag`) represent specific customer attributes that are essential for the platform's operations.\n\n1. **Seeder**\n\n   - **Definition**: A `seeder` is typically a customer who initiates activity on the platform, possibly influencing others to join or increasing platform liquidity.\n   - **Importance**: Identifying seeders helps in recognizing influential customers who can drive growth or activity within the platform.\n\n2. **Virtual Flag**\n\n   - **Definition**: The `virtual_flag` indicates whether an account is virtual or real. Virtual accounts may be used for testing, simulations, or as placeholders.\n   - **Importance**: Distinguishing between virtual and real accounts is crucial for accurate reporting, analytics, and ensuring that virtual activities do not skew operational metrics.\n\n3. **System Flag**\n\n   - **Definition**: The `system_flag` denotes accounts generated by the system, such as automated accounts used for internal processes or system checks.\n   - **Importance**: Identifying system accounts prevents them from being misclassified as customer activity, which could affect data analysis and business decisions.\n\n4. **Cloned Flag**\n\n   - **Definition**: A `cloned_flag` indicates that an account is a duplicate or has been cloned from another account, possibly without authorization.\n   - **Importance**: Detecting cloned accounts is vital for fraud prevention, security, and maintaining the integrity of the customer base.\n\n#### **Challenges in Prediction**\n\n1. **Data Sparsity**\n\n   - **Sparse Timestamps**: Fields like `first_trade_time`, `first_offramp_time`, and `first_onramp_time` contain sparse data, making it challenging to extract time-based features.\n   - **Missing Demographics**: Missing values in `gender` and `dob` can hinder demographic-based modeling.\n\n2. **Imbalanced Classes**\n\n   - **Uneven Distribution**: The target flags may have an imbalanced distribution (e.g., very few accounts are cloned), which can bias models towards the majority class.\n   - **Impact on Evaluation**: Imbalanced data requires careful handling to ensure that the model's performance is not overstated.\n\n3. **Feature Correlation**\n\n   - **Interrelated Features**: Some features may be correlated with each other or with the target variables, necessitating feature selection or dimensionality reduction techniques.\n\n4. **Anonymized Data**\n\n   - **Limited Personal Identifiers**: With anonymized data to protect privacy, some potentially predictive personal identifiers are unavailable, requiring creative feature engineering.\n\n#### **Implications of Accurate Predictions**\n\n1. **Enhanced Security**\n\n   - **Fraud Detection**: Accurately predicting `cloned_flag` and `system_flag` helps in early detection of fraudulent accounts and activities.\n   - **Risk Mitigation**: Reducing the risk of financial losses and reputational damage.\n\n2. **Operational Efficiency**\n\n   - **Automation**: Automating the classification of accounts reduces manual effort and speeds up processes.\n   - **Resource Allocation**: Allows the platform to focus resources on high-risk areas.\n\n3. **Business Growth**\n\n   - **Customer Engagement**: Identifying `seeder` customers can inform targeted marketing strategies to leverage their influence.\n   - **Service Personalization**: Understanding customer types enables the customization of services and offerings.\n\n4. **Regulatory Compliance**\n\n   - **KYC and AML**: Ensures compliance with regulations by correctly classifying and monitoring customer accounts.\n   - **Audit Preparedness**: Accurate records facilitate smoother audits and reporting.\n\n---\n\n### **Data Exploration Insights**\n\n#### **Customer Features Data**\n\n- **Temporal Features**: Utilize `sign_up_date` and `created_at` to derive features like account age, sign-up trends over time, or activity duration.\n- **Activity Indicators**: Presence or absence of `first_trade_time`, `first_offramp_time`, and `first_onramp_time` can serve as indicators of customer engagement levels.\n- **Demographic Features**: Even with missing values, `gender` and `dob` can be valuable predictors when available. Techniques like imputation or modeling missingness as a feature can be applied.\n\n#### **Balance Features Data**\n\n- **Financial Behavior**: Analyze `balance` and `frozen_balance` to understand customer financial activity patterns.\n- **Currency Preferences**: The `currency_code` can reveal customer preferences or market engagement.\n- **Temporal Dynamics**: Changes in balances over time (if multiple snapshots are available) can provide insights into transactional behavior.\n\n---\n\n### **Modeling Strategies**\n\n#### **Handling Imbalanced Data**\n\n- **Resampling Techniques**: Apply oversampling (e.g., SMOTE) or undersampling methods to balance the classes.\n- **Algorithm Selection**: Use algorithms that are robust to class imbalance, such as gradient boosting or random forests.\n- **Cost-Sensitive Learning**: Adjust the classification threshold or incorporate class weights to penalize misclassification of minority classes.\n\n#### **Feature Engineering**\n\n- **Derived Features**: Create new features like:\n\n  - **Account Age**: Difference between `snapshot_timestamp` and `created_at`.\n  - **Activity Flags**: Binary indicators for whether `first_trade_time`, `first_offramp_time`, or `first_onramp_time` are present.\n  - **Balance Ratios**: Ratios between `balance` and `frozen_balance`.\n\n- **Temporal Patterns**: Capture trends or patterns over time if temporal data is available.\n\n#### **Multi-Label Classification Approaches**\n\n- **Problem Transformation Methods**:\n\n  - **Binary Relevance**: Treat each flag as a separate binary classification problem.\n  - **Classifier Chains**: Model dependencies between the target flags by chaining classifiers.\n\n- **Algorithm Adaptation Methods**:\n\n  - Use algorithms inherently designed for multi-label classification, such as Multi-Label k-Nearest Neighbors (MLkNN) or neural networks with multi-output layers.\n\n#### **Model Evaluation**\n\n- **Cross-Validation**: Employ stratified k-fold cross-validation to ensure robust performance estimates, especially important with imbalanced data.\n- **Evaluation Metrics**: Besides Macro F1 Score, monitor other metrics like Precision, Recall, and AUC-ROC for each class to gain a comprehensive understanding of model performance.\n\n---\n\n### **Potential Pitfalls and Mitigation**\n\n1. **Overfitting**\n\n   - **Risk**: Models may overfit to the training data, especially with high-dimensional feature spaces.\n   - **Mitigation**: Use regularization techniques, cross-validation, and limit the complexity of the model.\n\n2. **Data Leakage**\n\n   - **Risk**: Including features that are not available at the time of prediction or that leak information about the target variable.\n   - **Mitigation**: Ensure that all features used are valid and available in a real-world prediction scenario.\n\n3. **Interpretability**\n\n   - **Challenge**: Complex models may be less interpretable.\n   - **Solution**: Use explainable AI techniques like SHAP values or feature importance plots to understand model decisions.\n\n---\n\n### **Ethical Considerations**\n\n- **Bias and Fairness**: Be cautious of introducing or perpetuating biases, especially if demographic features are used.\n- **Privacy**: Respect the anonymized nature of the data and avoid attempts to de-anonymize or infer personal identities.\n- **Transparency**: Aim for models that can provide explanations for their predictions, which is important in financial contexts.\n\n---\n\n### **Real-World Application Scenarios**\n\n1. **Fraud Prevention Systems**\n\n   - **Use Case**: Implementing real-time fraud detection mechanisms that flag suspicious accounts based on model predictions.\n   - **Benefit**: Enhances security and customer trust.\n\n2. **Customer Segmentation**\n\n   - **Use Case**: Segmenting customers for targeted marketing campaigns or personalized service offerings.\n   - **Benefit**: Increases customer engagement and satisfaction.\n\n3. **Regulatory Reporting**\n\n   - **Use Case**: Automating compliance reporting by accurately classifying accounts according to regulatory requirements.\n   - **Benefit**: Reduces manual effort and ensures timely compliance.\n\n---\n\n### **Conclusion**\n\nThe **Customer Flags Prediction Challenge** offers a complex, real-world problem that sits at the intersection of data science, finance, and technology. Participants will not only apply technical skills in machine learning and data analysis but also gain insights into the operational challenges faced by digital financial platforms.\n\nBy diving deep into the domain and understanding the intricacies of the problem, participants can develop robust models that have the potential to make significant impacts in real-world applications, from enhancing security measures to improving customer experiences.\n\n**Your contributions could shape the future of how financial platforms understand and interact with their customers. We encourage you to explore the data thoroughly, think creatively, and consider the broader implications of your models.**\n\n**Good luck, and we look forward to seeing your innovative solutions!**\n\n---\n\n*For further inquiries or discussions about the domain and problem specifics, please engage in the competition's discussion forum or reach out to the organizers directly.*",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "# **Submission Guidelines and Scoring Details**\n\nIn the **Customer Flags Prediction Challenge**, your submissions will be evaluated based on how accurately you predict the four binary customer flags. This document provides detailed instructions on how your submissions will be scored and how you should format your submission files.\n\n---\n\n## **Scoring Methodology**\n\n### **Evaluation Metric: Macro Averaged F1 Score**\n\nYour model's performance will be assessed using the **Macro Averaged F1 Score**, a metric suitable for multi-label classification tasks, especially when dealing with imbalanced datasets.\n\n#### **What is the Macro F1 Score?**\n\n- **F1 Score**: The F1 score is the harmonic mean of precision and recall for a single class.\n  \n  \\[\n  \\text{F1 Score} = 2 \\times \\frac{\\text{Precision} \\times \\text{Recall}}{\\text{Precision} + \\text{Recall}}\n  \\]\n\n- **Macro Averaging**: In macro averaging, the F1 score is calculated independently for each class (in this case, each flag) and then averaged.\n\n  \\[\n  \\text{Macro F1 Score} = \\frac{1}{N} \\sum_{i=1}^{N} \\text{F1 Score}_i\n  \\]\n\n  where \\( N \\) is the number of classes (4 in this competition).\n\n#### **Why Use Macro F1 Score?**\n\n- **Class Balance**: It treats all classes equally, which is important when the classes are imbalanced.\n- **Comprehensive Evaluation**: Considers both false positives and false negatives.\n\n#### **Scoring Procedure**\n\n1. **Per-Flag Evaluation**: For each of the four flags (`seeder`, `virtual_flag`, `system_flag`, `cloned_flag`), calculate the F1 score separately.\n2. **Average Calculation**: Compute the average of these four F1 scores to get the Macro F1 Score.\n3. **Final Score**: The final score used for ranking on the leaderboard is the Macro F1 Score.\n\n#### **Example Calculation**\n\nSuppose your model achieves the following F1 scores:\n\n- F1 Score for `seeder`: 0.80\n- F1 Score for `virtual_flag`: 0.75\n- F1 Score for `system_flag`: 0.85\n- F1 Score for `cloned_flag`: 0.65\n\nThen, the Macro F1 Score is:\n\n\\[\n\\text{Macro F1 Score} = \\frac{0.80 + 0.75 + 0.85 + 0.65}{4} = \\frac{3.05}{4} = 0.7625\n\\]\n\n---\n\n## **Submission Format**\n\nYour submission should be a CSV file named `submission.csv` containing your predictions for each customer in the test set. The file must adhere to the following specifications:\n\n### **File Format**\n\n- **File Type**: CSV (Comma-Separated Values)\n- **Encoding**: UTF-8\n- **Column Headers**: Include a header row with the following column names:\n  - `customer_id`\n  - `seeder`\n  - `virtual_flag`\n  - `system_flag`\n  - `cloned_flag`\n\n### **Columns Description**\n\n1. **customer_id**\n   - **Type**: String\n   - **Description**: The unique identifier for each customer.\n   - **Requirement**: Must match the `customer_id`s provided in the test set exactly.\n\n2. **seeder**\n   - **Type**: Integer (0 or 1)\n   - **Description**: Your prediction for the `seeder` flag.\n   - **Values**: \n     - `1` if you predict the customer is a seeder.\n     - `0` if you predict the customer is not a seeder.\n\n3. **virtual_flag**\n   - **Type**: Integer (0 or 1)\n   - **Description**: Your prediction for the `virtual_flag`.\n   - **Values**:\n     - `1` if you predict the customer is a virtual account.\n     - `0` if you predict the customer is a real account.\n\n4. **system_flag**\n   - **Type**: Integer (0 or 1)\n   - **Description**: Your prediction for the `system_flag`.\n   - **Values**:\n     - `1` if you predict the customer is a system-generated account.\n     - `0` if you predict the customer is not a system-generated account.\n\n5. **cloned_flag**\n   - **Type**: Integer (0 or 1)\n   - **Description**: Your prediction for the `cloned_flag`.\n   - **Values**:\n     - `1` if you predict the customer account is cloned.\n     - `0` if you predict the customer account is not cloned.\n\n### **Formatting Requirements**\n\n- **Order of Rows**: The `customer_id`s in your submission must correspond exactly to those in the test set. The order of the rows does not matter, but each `customer_id` must be present exactly once.\n- **No Missing Values**: Ensure there are no missing values in any of the columns.\n- **Data Types**: Predictions must be integers (`0` or `1`), not strings or floats.\n- **No Additional Columns**: Do not include any extra columns besides the ones specified.\n- **No Index Column**: If exporting from pandas or similar tools, ensure that the index is not included as an extra column.\n\n### **Sample Submission File**\n\nHere is an example of how your `submission.csv` file should look:\n\n```csv\ncustomer_id,seeder,virtual_flag,system_flag,cloned_flag\n1,0,1,0,0\n2,1,0,0,1\n3,0,0,0,0\n4,1,0,1,0\n5,0,1,0,0\n...\n```\n\n### **Common Pitfalls to Avoid**\n\n- **Incorrect `customer_id`s**: Make sure that all `customer_id`s in your submission match those in the test set and that there are no duplicates or missing IDs.\n- **Data Type Errors**: Ensure that your predictions are integers (`0` or `1`), not floats (e.g., `0.0`, `1.0`) or strings (e.g., `\"0\"`, `\"1\"`).\n- **Extra Columns or Rows**: Do not include any additional columns or rows (e.g., a header row for the index).\n\n---\n\n## **Submission Procedure**\n\n1. **Generate Predictions**\n\n   - Use your trained model(s) to predict the flags for each customer in the test set.\n   - Ensure that the predictions are in the correct format.\n\n2. **Create Submission File**\n\n   - Compile your predictions into a CSV file named `submission.csv`.\n   - Verify that the file meets all formatting requirements.\n\n3. **Validate Submission File**\n\n   - Open the CSV file in a text editor or spreadsheet software to confirm the structure.\n   - Check for any formatting issues, such as unintended quotation marks or extra delimiters.\n\n4. **Submit on Kaggle**\n\n   - Log in to your Kaggle account.\n   - Navigate to the competition's **\"Submit Predictions\"** page.\n   - Upload your `submission.csv` file.\n   - Confirm the submission.\n\n5. **Check Leaderboard**\n\n   - After submitting, your submission will be scored based on the evaluation metric.\n   - Your score and ranking will appear on the public leaderboard.\n\n---\n\n## **Submission Limits and Rules**\n\n- **Daily Submission Limit**: You can submit up to **5** times per day.\n- **Total Submission Limit**: There is a maximum total of **[Total Submissions Allowed]** submissions throughout the competition.\n- **Final Submission**: Only your **last** submission before the competition deadline will be considered for the final evaluation.\n\n### **Leaderboard**\n\n- **Public Leaderboard**: Displays scores based on a portion of the test set.\n- **Private Leaderboard**: Final rankings are determined using the remaining portion of the test set after the competition ends.\n\n---\n\n## **Tips for Successful Submissions**\n\n- **Consistency**: Double-check that the `customer_id`s in your submission align perfectly with those in the test set.\n- **Version Control**: Keep track of different versions of your models and submission files to understand what works best.\n- **Validation**: Use cross-validation and a hold-out validation set to estimate your model's performance before submitting.\n- **Efficiency**: Given the submission limits, prioritize submitting your best models and avoid using all submissions early in the day.\n\n---\n\n## **Troubleshooting Submission Errors**\n\n- **Invalid File Format**: Ensure your file is saved as a CSV with UTF-8 encoding.\n- **Incorrect Column Names**: Column headers must match exactly (`customer_id`, `seeder`, `virtual_flag`, `system_flag`, `cloned_flag`).\n- **Missing Predictions**: All `customer_id`s from the test set must be included with predictions for each flag.\n- **Data Type Issues**: Predictions must be integers (`0` or `1`), not floats or strings.\n\n---\n\n## **Example Code for Creating Submission File**\n\nHere's an example in Python using pandas to help you format your submission correctly:\n\n```python\nimport pandas as pd\n\n# Load test data\ntest_df = pd.read_csv('test_customer_features.csv')\n\n# Assume you have a trained model called 'model'\n# And a function 'predict_flags' that returns predictions for the four flags\n\n# Generate predictions\n# This should be replaced with your actual prediction code\npredictions = predict_flags(test_df)\n\n# Create a submission DataFrame\nsubmission_df = pd.DataFrame({\n    'customer_id': test_df['customer_id'],\n    'seeder': predictions['seeder'],\n    'virtual_flag': predictions['virtual_flag'],\n    'system_flag': predictions['system_flag'],\n    'cloned_flag': predictions['cloned_flag']\n})\n\n# Ensure predictions are integers\nsubmission_df['seeder'] = submission_df['seeder'].astype(int)\nsubmission_df['virtual_flag'] = submission_df['virtual_flag'].astype(int)\nsubmission_df['system_flag'] = submission_df['system_flag'].astype(int)\nsubmission_df['cloned_flag'] = submission_df['cloned_flag'].astype(int)\n\n# Save to CSV\nsubmission_df.to_csv('submission.csv', index=False)\n```\n\n---\n\n## **Final Reminders**\n\n- **Deadline**: Make sure to submit your final predictions before the competition deadline.\n- **Compliance**: Ensure your submission complies with all competition rules and guidelines.\n- **Best Practices**: Keep your code and models well-documented for potential review and learning.\n\n---\n\nBy carefully following these guidelines, you'll help ensure that your submissions are successfully processed and fairly evaluated. Good luck with your modeling, and we look forward to seeing your innovative solutions in the **Customer Flags Prediction Challenge**!\n\n---\n\nIf you have any questions or encounter issues with your submission, please refer to the **FAQs** or post in the competition's **Discussion Forum** for assistance.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "##ENTRY IN THIS COMPETITION CONSTITUTES YOUR ACCEPTANCE OF THESE OFFICIAL COMPETITION RULES.\n\n**[See Section 3.18 for defined terms](rules#18.-terms)**\n\n*The Competition named below is a skills-based competition to promote and further the field of data science. You must register via the Competition Website to enter. To enter the Competition, you must agree to these Official Competition Rules, which incorporate by reference the provisions and content of the Competition Website and any Specific Competition Rules herein (collectively, the \"Rules\"). Please read these Rules carefully before entry to ensure you understand and agree. You further agree that Submission in the Competition constitutes agreement to these Rules. You may not submit to the Competition and are not eligible to receive the prizes associated with this Competition unless you agree to these Rules. These Rules form a binding legal agreement between you and the Competition Sponsor with respect to the Competition. Your competition Submissions  must conform to the requirements stated on the Competition Website. Your Submissions will be scored based on the evaluation metric described on the Competition Website. Subject to compliance with the Competition Rules, Prizes, if any, will be awarded to Participants with the best scores, based on the merits of the data science models submitted. See below for the complete Competition Rules.*\n\n**You cannot sign up to Kaggle from multiple accounts and therefore you cannot enter or submit from multiple accounts.**\n\n<h3>1. COMPETITION-SPECIFIC TERMS</h3>\n<h4>1. COMPETITION TITLE</h4> [INSERT]\n<h4>2. COMPETITION SPONSOR</h4>  [INSERT]\n<h4>3. COMPETITION SPONSOR ADDRESS</h4> [INSERT]\n<h4>4. COMPETITION WEBSITE</h4> https://www.kaggle.com/competitions/[INSERT]\n<h4>5. NO MONETARY PRIZES IS AVAILABLE</h4> \n<h4>6. DATA ACCESS AND USE</h4> [INSERT]\n\n\n###2. COMPETITION-SPECIFIC RULES \nIn addition to the provisions of the General Competition Rules below, you understand and agree to these Competition-Specific Rules required by the Competition Sponsor:\n\n####1. TEAM LIMITS\na. The maximum Team size is five (5).</h5>\nb. Team mergers are allowed and can be performed by the Team leader. In order to merge, the combined Team must have a total Submission count less than or equal to the maximum allowed as of the Team Merger Deadline. The maximum allowed is the number of Submissions per day multiplied by the number of days the competition has been running.</h5>\n\n####2. SUBMISSION LIMITS\na. You may submit a maximum of 20 Submissions per day.</h5>\nb. You may select up to two (2) Final Submissions for judging.</h5>\n\n####3. COMPETITION TIMELINE\na. Competition Timeline dates (including Entry Deadline, Final Submission Deadline, Start Date, and Team Merger Deadline, as applicable) are reflected on the competition’s Overview > Timeline page.</h5>\n\n####4. COMPETITION DATA\n\na. Data Access and Use. [CHOOSE ONE OF THE 3 OPTIONS BELOW BASED ON WHAT THE SPONSOR CHOOSES IN THE SOW.]</h5>\n\n1. [*Competition Use only is checked*: You may access and use the Competition Data only for participating in the Competition and on Kaggle.com forums. The Competition Sponsor reserves the right to disqualify any Participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.]</h6>\n\n2. [*Competition Use and Non-Commercial & Academic Research is checked*: You may access and use the Competition Data for non-commercial purposes only, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any Participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.]</h6>\n\n3. [*Competition Use and Commercial are checked*: You may access and use the Competition Data for any purpose, whether commercial or non-commercial, including for participating in the Competition and on Kaggle.com forums, and for academic research and education. The Competition Sponsor reserves the right to disqualify any Participant who uses the Competition Data other than as permitted by the Competition Website and these Rules.]</h6>\n\n4. [*ADD IN THE FOLLOWING, IN ADDITION TO THE CHOSEN SECTION ABOVE, IF SPECIFIC LICENSE IS CHECKED*: The Competition Data is also subject to the following terms and conditions: [INSERT URL]. </h6>\n\nb. Data Security. </h5>\n\n1. You agree to use reasonable and suitable measures to prevent persons who have not formally agreed to these Rules from gaining access to the Competition Data. You agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Competition Data to any party not participating in the Competition. You agree to notify Kaggle immediately upon learning of any possible unauthorized transmission of or unauthorized access to the Competition Data and agree to work with Kaggle to rectify any unauthorized transmission or access.</h6>\n\n####5. WINNER LICENSE [INSERT ONLY THE RELEVANT LICENSE LANGUAGE FOR THE COMPETITION.]\n\na. Under Section 2.8 (Winners Obligations) of the General Rules below, you hereby grant and will grant the Competition Sponsor the following license(s) with respect to your Submission if you are a Competition winner:</h5>\n\n1. [*Non-Exclusive*: You hereby grant and will grant to Competition Sponsor and its designees a worldwide, non-exclusive, sub-licensable, transferable, fully paid-up, royalty-free, perpetual, irrevocable right to use, reproduce, distribute, create derivative works of, publicly perform, publicly display, digitally perform, make, have made, sell, offer for sale and import your winning Submission and the source code used to generate the Submission, in any media now known or developed in the future, for any purpose whatsoever, commercial or otherwise, without further approval by or payment to you.]</h6>\n \n2. [*Open Source: You hereby license and will license your winning Submission and the source code used to generate the Submission under an Open Source Initiative-approved license (see [www.opensource.org] (http://www.opensource.org)) that in no event limits commercial use of such code or model containing or depending on such code. </h6>\n\n3. For generally commercially available software that you used to generate your Submission that is not owned by you, but that can be procured by the Competition Sponsor without undue expense, you do not need to grant the license in the preceding Section for that software. </h6>\n\n4. In the event that input data or pretrained models with an incompatible license are used to generate your winning solution, you do not need to grant an open source license in the preceding Section for that data and/or model(s). </h6>\n\nb. You may be required by the Sponsor to provide a detailed description of how the winning Submission was generated, to the Competition Sponsor’s specifications, as outlined in Section 2.8, Winner’s Obligations. This may include a detailed description of methodology, where one must be able to reproduce the approach by reading the description, and includes a detailed explanation of the architecture, preprocessing, loss function, training details, hyper-parameters, etc. The description should also include a link to a code repository with complete and detailed instructions so that the results obtained can be reproduced.</h7>\n \n####6. EXTERNAL DATA AND TOOLS\n\na. You may use data other than the Competition Data (“External Data”) to develop and test your Submissions. However, you will ensure the External Data is either publicly available and equally accessible to use by all Participants of the Competition for purposes of the competition at no cost to the other Participants, or satisfies the Reasonableness criteria as outlined in Section 2.6.b below. The ability to use External Data under this Section does not limit your other obligations under these Competition Rules, including but not limited to Section 2.8 (Winners Obligations). </h5>\n\nb. The use of external data and models is acceptable unless specifically prohibited by the Host. Because of the potential costs or restrictions (e.g., “geo restrictions”) associated with obtaining rights to use external data or certain software and associated tools, their use must be “reasonably accessible to all” and of “minimal cost”. Also, regardless of the cost challenges as they might affect all Participants during the course of the competition, the costs of potentially procuring a license for software used to generate a Submission, must also be considered. The Host will employ an assessment of whether or not the following criteria can exclude the use of the particular LLM, data set(s), or tool(s):</h5>\n\n1. Are Participants being excluded from a competition because of the \"excessive\" costs for access to certain LLMs, external data, or tools that might be used by other Participants. The Host will assess the excessive cost concern by applying a “Reasonableness” standard (the “Reasonableness Standard”). The Reasonableness Standard will be determined and applied by the Host in light of things like cost thresholds and accessibility.</h6>\n\n2. By way of example only, a small subscription charge to use additional elements of a large language model such as Gemini Advanced are acceptable if meeting the Reasonableness Standard of Sec. 8.2. Purchasing a license to use a proprietary dataset that exceeds the cost of a prize in the competition would not be considered reasonable.</h6>\n\nc. Automated Machine Learning Tools (“AMLT”)</h5>\n\n1. Individual Participants and Teams may use automated machine learning tool(s) (“AMLT”) (e.g., Google toML, H2O Driverless AI, etc.) to create a Submission, provided that the Participant or Team ensures that they have an appropriate license to the AMLT such that they are able to comply with the Competition Rules. </h6>\n\n####7. ELIGIBILITY\n\na. Unless otherwise stated in the Competition-Specific Rules above or prohibited by internal policies of the Competition Entities, employees, interns, contractors, officers and directors of Competition Entities may enter and participate in the Competition, but are not eligible to win any Prizes. \"Competition Entities\" means the Competition Sponsor, Kaggle Inc., and their respective parent companies, subsidiaries and affiliates. If you are such a Participant from a Competition Entity, you are subject to all applicable internal policies of your employer with respect to your participation.</h5>\n\n####8. WINNER’S OBLIGATIONS\n\na. As a condition to being awarded a Prize, a Prize winner must fulfill the following obligations:</h5>\n\n1. Deliver to the Competition Sponsor the final model's software code as used to generate the winning Submission and associated documentation. The delivered software code should follow [these documentation guidelines][5], must be capable of generating the winning Submission, and contain a description of resources required to build and/or run the executable code successfully. For avoidance of doubt, delivered software code should include training code, inference code, and a description of the required computational environment. \n\na. To the extent that the final model’s software code includes generally commercially available software that is not owned by you, but that can be procured by the Competition Sponsor without undue expense, then instead of delivering the code for that software to the Competition Sponsor, you must identify that software, method for procuring it, and any parameters or other information necessary to replicate the winning Submission; Individual Participants and Teams who create a Submission using an AMLT may win a Prize. However, for clarity, the potential winner’s Submission must still meet the requirements of these Rules, including but not limited to Section 2.5 (Winners License), Section 2.8 (Winners Obligations), and Section 3.14 (Warranty, Indemnity, and Release).” </h6>\n\nb. Individual Participants and Teams who create a Submission using an AMLT may win a Prize. However, for clarity, the potential winner’s Submission must still meet the requirements of these Rules,</h6>\n\n2. Grant to the Competition Sponsor the license to the winning Submission stated in the Competition Specific Rules above, and represent that you have the unrestricted right to grant that license;</h6>\n\n3. Sign and return all Prize acceptance documents as may be required by Competition Sponsor or Kaggle, including without limitation: (a) eligibility certifications; (b) licenses, releases and other agreements required under the Rules; and (c) U.S. tax forms (such as IRS Form W-9 if U.S. resident, IRS Form W-8BEN if foreign resident, or future equivalents).</h6>\n\n####9. GOVERNING LAW\n\na. Unless otherwise provided in the Competition Specific Rules above, all claims arising out of or relating to these Rules will be governed by California law, excluding its conflict of laws rules, and will be litigated exclusively in the Federal or State courts of Santa Clara County, California, USA. The parties consent to personal jurisdiction in those courts. If any provision of these Rules is held to be invalid or unenforceable, all remaining provisions of the Rules will remain in full force and effect.</h5>\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "# **Customer Flags Prediction Challenge**\n\n*Predicting key customer attributes using activity and balance data.*\n\n---\n\n## **Overview**\n\nWelcome to the **Customer Flags Prediction Challenge**! This competition invites data enthusiasts to delve into real-world customer data and predict essential binary attributes that define customer profiles within our platform. Your mission is to develop models that accurately predict the following customer flags:\n\n- **seeder**\n- **virtual_flag**\n- **system_flag**\n- **cloned_flag**\n\n---\n\n## **The Challenge**\n\n### **Objective**\n\nDevelop a machine learning model (or models) to predict the four binary customer flags based on provided customer features and balance data.\n---\n\n## **Datasets**\n\nYou will work with two primary datasets:\n\n### **1. Customer Features Data**\n\n**Filename**: `customer_features_*.csv`\n\nThis dataset contains detailed information about each customer.\n\n**Key Columns:**\n\n- `customer_id`: Unique identifier for each customer.\n- `sign_up_date`, `created_at`: Timestamps indicating when the customer signed up and when the account was created.\n- `virtual_flag`, `system_flag`, `cloned_flag`: Binary flags indicating specific customer attributes (the target variables).\n- `first_trade_time`, `first_offramp_time`, `first_onramp_time`: Timestamps of the customer's first trade, offramp, and onramp activities.\n- `gender`, `dob`: Demographic details (may contain missing values).\n- `banker_score`: A score representing customer activity levels.\n- `seeder`: A binary indicator of whether the customer is a seeder.\n\n### **2. Balance Features Data**\n\n**Filename**: `balance_features_*.csv`\n\nThis dataset provides information about the customers' account balances.\n\n**Key Columns:**\n\n- `customer_id`: Unique identifier linking customers to balance information.\n- `currency_code`: Numeric code representing the currency type.\n- `balance`, `frozen_balance`: Current available and frozen balances for each customer.\n- `snapshot_timestamp`: Timestamp when the balance snapshot was taken.\n\n---\n\n## **Evaluation**\n\nYour predictions will be evaluated based on accuracy across all four binary flags. The specific evaluation metric is:\n\n- **Evaluation Metric**: [Macro F1 Score](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.f1_score.html) for multi-label classification.\n\n---\n\n## **Getting Started**\n\n### **1. Explore the Data**\n\n- Perform exploratory data analysis to understand feature distributions, correlations, and potential data quality issues.\n- Identify missing values and consider appropriate imputation methods.\n\n### **2. Feature Engineering**\n\n- Create new features that might enhance model performance (e.g., time since sign-up, age from `dob`).\n- Consider encoding categorical variables and normalizing numerical features.\n\n### **3. Model Development**\n\n- Experiment with various classification algorithms suited for multi-label classification\n- Utilize techniques like cross-validation to assess model generalization.\n\n### **4. Submission**\n\n- Generate predictions for the test set and format them according to the submission guidelines.\n- Ensure that your submission includes predictions for all four target variables.\n\n---\n\n## **Resources**\n\n- **Discussion Forum**: Engage with the community, ask questions, and share insights.\n- **FAQs**: Check the Frequently Asked Questions section for common queries.\n\n---\n\n## **Timeline**\n\n- **Competition Launch**: 14 November 2024\n- **Submission Deadline**: 31 March 2025\n- **Winner Announcement**: 15 April 2025\n\n---\n\n## **Prizes**\n\nSWAG and INFINITE RIZZ\n\n---\n\n## **Rules**\n\n- **Team Size**: Maximum of 5 members per team.\n- **Submission Limit**: 20 submissions per day.\n- **Data Usage**: Use of external data is prohibited to ensure a level playing field.\n- **Code Sharing**: Sharing of code is allowed only through the competition's discussion forums.\n\n---\n\n## **Join the Challenge!**\n\nThis is your opportunity to tackle a real-world problem, enhance your data science skills, and contribute to valuable customer insights. Whether you're a seasoned professional or a budding enthusiast, your participation is highly valued.\n\nWe can't wait to see the innovative solutions you'll bring to the **Customer Flags Prediction Challenge**!\n\n**Good luck and happy coding!**\n\n---\n\n*For any questions or clarifications, please refer to the discussion forum or contact the competition organizers at nghiadt22@gmail.com.*",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "foundational-rules",
      "content": "The following Kaggle Competition Foundational Rules (“ Foundational Rules ”) apply to every competition regardless of whether the Sponsor creates competition-specific rules. Any competition-specific rules provided by the Sponsor are in addition to these rules, and in the case of any conflict or inconsistency, these Foundational Rules control and nullify contrary competition-specific rules.\n###GENERAL COMPETITION RULES - BINDING AGREEMENT\n####1. ELIGIBILITY\na. To be eligible to enter the Competition, you must be:</h5>\n1. a registered account holder at Kaggle.com; </h6>\n2. the older of 18 years old or the age of majority in your jurisdiction of residence (unless otherwise agreed to by Competition Sponsor and appropriate parental/guardian consents have been obtained by Competition Sponsor); </h6>\n3. not a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, or North Korea; and</h6>\n4. not a person or representative of an entity under U.S. export controls or sanctions (see: [https://www.treasury.gov/resourcecenter/sanctions/Programs/Pages/Programs.aspx][1]).</h6>\n\nb. Competitions are open to residents of the United States and worldwide, except that if you are a resident of Crimea, so-called Donetsk People's Republic (DNR) or Luhansk People's Republic (LNR), Cuba, Iran, Syria, North Korea, or are subject to U.S. export controls or sanctions, you may not enter the Competition. Other local rules and regulations may apply to you, so please check your local laws to ensure that you are eligible to participate in skills-based competitions. The Competition Host reserves the right to forego or award alternative Prizes where needed to comply with local laws. If a winner is located in a country where prizes cannot be awarded, then they are not eligible to receive a prize.</h5>\n\nc. If you are entering as a representative of a company, educational institution or other legal entity, or on behalf of your employer, these rules are binding on you, individually, and the entity you represent or where you are an employee. If you are acting within the scope of your employment, or as an agent of another party, you warrant that such party or your employer has full knowledge of your actions and has consented thereto, including your potential receipt of a Prize. You further warrant that your actions do not violate your employer's or entity's policies and procedures.</h5>   \n\nd. The Competition Sponsor reserves the right to verify eligibility and to adjudicate on any dispute at any time. If you provide any false information relating to the Competition concerning your identity, residency, mailing address, telephone number, email address, ownership of right, or information required for entering the Competition, you may be immediately disqualified from the Competition.</h5>\n\n####2. SPONSOR AND HOSTING PLATFORM\n\na. The Competition is sponsored by Competition Sponsor named above. The Competition is hosted on behalf of Competition Sponsor by Kaggle Inc. (\"Kaggle\"). Kaggle is an independent contractor of Competition Sponsor, and is not a party to this or any agreement between you and Competition Sponsor. You understand that Kaggle has no responsibility with respect to selecting the potential Competition winner(s) or awarding any Prizes. Kaggle will perform certain administrative functions relating to hosting the Competition, and you agree to abide by the provisions relating to Kaggle under these Rules. As a Kaggle.com account holder and user of the Kaggle competition platform, remember you have accepted and are subject to the Kaggle Terms of Service at [www.kaggle.com/terms][2] in addition to these Rules.</h5>\n\n####3. COMPETITION PERIOD\na. For the purposes of Prizes, the Competition will run from the Start Date and time to the Final Submission Deadline (such duration the “Competition Period”). The Competition Timeline is subject to change, and Competition Sponsor may introduce additional hurdle deadlines during the Competition Period. Any updated or additional deadlines will be publicized on the Competition Website. It is your responsibility to check the Competition Website regularly to stay informed of any deadline changes. YOU ARE RESPONSIBLE FOR DETERMINING THE CORRESPONDING TIME ZONE IN YOUR LOCATION.</h5>\n\n####4. COMPETITION ENTRY\na. NO PURCHASE NECESSARY TO ENTER OR WIN. To enter the Competition, you must register on the Competition Website prior to the Entry Deadline, and follow the instructions for developing and entering your Submission through the Competition Website. Your Submissions must be made in the manner and format, and in compliance with all other requirements, stated on the Competition Website (the \"Requirements\"). Submissions must be received before any Submission deadlines stated on the Competition Website. Submissions not received by the stated deadlines will not be eligible to receive a Prize.</h5>\nb. Submissions may not use or incorporate information from hand labeling or human prediction of the validation dataset or test data records.</h5>\nc. If the Competition is a multi-stage competition with temporally separate training and/or test data, one or more valid Submissions may be required during each Competition stage in the manner described on the Competition Website in order for the Submissions to be Prize eligible.</h5>\nd. Submissions are void if they are in whole or part illegible, incomplete, damaged, altered, counterfeit, obtained through fraud, or late. Competition Sponsor reserves the right to disqualify any entrant who does not follow these Rules, including making a Submission that does not meet the Requirements. </h5>\n\n####5. INDIVIDUALS AND TEAMS\na. Individual Account. You may make Submissions only under one, unique Kaggle.com account. You will be disqualified if you make Submissions through more than one Kaggle account, or attempt to falsify an account to act as your proxy. You may submit up to the maximum number of Submissions per day as specified on the Competition Website. </h5>\nb. Teams. If permitted under the Competition Website guidelines, multiple individuals may collaborate as a Team; however, you may join or form only one Team. Each Team member must be a single individual with a separate Kaggle account. You must register individually for the Competition before joining a Team. You must confirm your Team membership to make it official by responding to the Team notification message sent to your Kaggle account. Team membership may not exceed the Maximum Team Size stated on the Competition Website.</h5>\nc. Team Merger. Teams may request to merge via the Competition Website. Team mergers may be allowed provided that: (i) the combined Team does not exceed the Maximum Team Size; (ii) the number of Submissions made by the merging Teams does not exceed the number of Submissions permissible for one Team at the date of the merger request; (iii) the merger is completed before the earlier of: any merger deadline or the Competition deadline; and (iv) the proposed combined Team otherwise meets all the requirements of these Rules. </h5>\nd. Private Sharing. No private sharing outside of Teams. Privately sharing code or data outside of Teams is not permitted. It's okay to share code if made available to all Participants on the forums.</h5>\n\n####6. SUBMISSION CODE REQUIREMENTS\na. Private Code Sharing. Unless otherwise specifically permitted under the Competition Website or Competition Specific Rules above, during the Competition Period, you are not allowed to privately share source or executable code developed in connection with or based upon the Competition Data or other source or executable code relevant to the Competition (“Competition Code”). This prohibition includes sharing Competition Code between separate Teams, unless a Team merger occurs. Any such sharing of Competition Code is a breach of these Competition Rules and may result in disqualification.</h5>\nb. Public Code Sharing. You are permitted to publicly share Competition Code, provided that such public sharing does not violate the intellectual property rights of any third party. If you do choose to share Competition Code or other such code, you are required to share it on Kaggle.com on the discussion forum or notebooks associated specifically with the Competition for the benefit of all competitors. By so sharing, you are deemed to have licensed the shared code under an Open Source Initiative-approved license (see [www.opensource.org][3]) that in no event limits commercial use of such Competition Code or model containing or depending on such Competition Code.</h5>\nc. Use of Open Source. Unless otherwise stated in the Specific Competition Rules above, if open source code is used in the model to generate the Submission, then you must only use open source code licensed under an Open Source Initiative-approved license (see [www.opensource.org][4]) that in no event limits commercial use of such code or model containing or depending on such code.</h5>\n\n####7. DETERMINING WINNERS\na. Each Submission will be scored and ranked by the evaluation metric stated on the Competition Website. During the Competition Period, the current ranking will be visible on the Competition Website's Public Leaderboard. The potential winner(s) are determined solely by the leaderboard ranking on the Private Leaderboard, subject to compliance with these Rules. The Public Leaderboard will be based on the public test set and the Private Leaderboard will be based on the private test set.</h5>\nb. In the event of a tie, the Submission that was entered first to the Competition will be the winner. In the event a potential winner is disqualified for any reason, the Submission that received the next highest score rank will be chosen as the potential winner.</h5>\n\n####8. NOTIFICATION OF WINNERS & DISQUALIFICATION\na. The potential winner(s) will be notified by email.</h5> \nb. If a potential winner (i) does not respond to the notification attempt within one (1) week from the first notification attempt or (ii) notifies Kaggle within one week after the Final Submission Deadline that the potential winner does not want to be nominated as a winner or does not want to receive a Prize, then, in each case (i) and (ii) such potential winner will not receive any Prize, and an alternate potential winner will be selected from among all eligible entries received based on the Competition’s judging criteria.</h5>\nc. In case (i) and (ii) above Kaggle may disqualify the Participant.  However, in case (ii) above, if requested by Kaggle, such potential winner may provide code and documentation to verify the Participant’s compliance with these Rules. If the potential winner provides code and documentation to the satisfaction of Kaggle, the Participant will not be disqualified pursuant to this paragraph.</h5>\nd. Competition Sponsor reserves the right to disqualify any Participant from the Competition if the Competition Sponsor reasonably believes that the Participant has attempted to undermine the legitimate operation of the Competition by cheating, deception, or other unfair playing practices or abuses, threatens or harasses any other Participants, Competition Sponsor or Kaggle.</h5>\ne. A disqualified Participant may be removed from the Competition leaderboard, at Kaggle's sole discretion. If a Participant is removed from the Competition Leaderboard, additional winning features associated with the Kaggle competition platform, for example Kaggle points or medals, may also not be awarded.</h5>\nf. The final leaderboard list will be publicly displayed at Kaggle.com. Determinations of Competition Sponsor are final and binding.</h5>\n\n####9. PRIZES\na. Prize(s) are as described on the Competition Website and are only available for winning during the time period described on the Competition Website. The odds of winning any Prize depends on the number of eligible Submissions received during the Competition Period and the skill of the Participants. </h5>\nb. All Prizes are subject to Competition Sponsor's review and verification of the Participant’s eligibility and compliance with these Rules, and the compliance of the winning Submissions with the Submissions Requirements. In the event that the Submission demonstrates non-compliance with these Competition Rules, Competition Sponsor may at its discretion take either of the following actions: (i) disqualify the Submission(s); or (ii) require the potential winner to remediate within one week after notice all issues identified in the Submission(s) (including, without limitation, the resolution of license conflicts, the fulfillment of all obligations required by software licenses, and the removal of any software that violates the software restrictions).</h5>\nc. A potential winner may decline to be nominated as a Competition winner in accordance with Section 3.8.</h5>\nd. Potential winners must return all required Prize acceptance documents within two (2) weeks following notification of such required documents, or such potential winner will be deemed to have forfeited the prize and another potential winner will be selected. Prize(s) will be awarded within approximately thirty (30) days after receipt by Competition Sponsor or Kaggle of the required Prize acceptance documents. Transfer or assignment of a Prize is not allowed. </h5>\ne. You are not eligible to receive any Prize if you do not meet the Eligibility requirements in Section 2.7 and Section 3.1 above.</h5>\nf. If a Team wins a monetary Prize, the Prize money will be allocated in even shares between the eligible Team members, unless the Team unanimously opts for a different Prize split and notifies Kaggle before Prizes are issued.</h5>\n\n####10. TAXES\na. ALL TAXES IMPOSED ON PRIZES ARE THE SOLE RESPONSIBILITY OF THE WINNERS. Payments to potential winners are subject to the express requirement that they submit all documentation requested by Competition Sponsor or Kaggle for compliance with applicable state, federal, local and foreign (including provincial) tax reporting and withholding requirements. Prizes will be net of any taxes that Competition Sponsor is required by law to withhold. If a potential winner fails to provide any required documentation or comply with applicable laws, the Prize may be forfeited and Competition Sponsor may select an alternative potential winner. Any winners who are U.S. residents will receive an IRS Form-1099 in the amount of their Prize.</h5>\n\n####11. GENERAL CONDITIONS\na. All federal, state, provincial and local laws and regulations apply.</h5>\n\n####12. PUBLICITY\na. You agree that Competition Sponsor, Kaggle and its affiliates may use your name and likeness for advertising and promotional purposes without additional compensation, unless prohibited by law.</h5>\n\n####13. PRIVACY\na. You acknowledge and agree that Competition Sponsor and Kaggle may collect, store, share and otherwise use personally identifiable information provided by you during the Kaggle account registration process and the Competition, including but not limited to, name, mailing address, phone number, and email address (“Personal Information”). Kaggle acts as an independent controller with regard to its collection, storage, sharing, and other use of this Personal Information, and will use this Personal Information in accordance with its Privacy Policy <[www.kaggle.com/privacy][6]>, including for administering the Competition. As a Kaggle.com account holder, you have the right to request access to, review, rectification, portability or deletion of any personal data held by Kaggle about you by logging into your account and/or contacting Kaggle Support at <[www.kaggle.com/contact][7]>.</h5>\nb. As part of Competition Sponsor performing this contract between you and the Competition Sponsor, Kaggle will transfer your Personal Information to Competition Sponsor, which acts as an independent controller with regard to this Personal Information. As a controller of such Personal Information, Competition Sponsor agrees to comply with all U.S. and foreign data protection obligations with regard to your Personal Information. Kaggle will transfer your Personal Information to Competition Sponsor in the country specified in the Competition Sponsor Address listed above, which may be a country outside the country of your residence. Such country may not have privacy laws and regulations similar to those of the country of your residence.</h5>\n\n####14. WARRANTY, INDEMNITY AND RELEASE \na. You warrant that your Submission is your own original work and, as such, you are the sole and exclusive owner and rights holder of the Submission, and you have the right to make the Submission and grant all required licenses.  You agree not to make any Submission that: (i) infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; or (ii) otherwise violates any applicable U.S. or foreign state or federal law.</h5>\nb. To the maximum extent permitted by law, you indemnify and agree to keep indemnified Competition Entities at all times from and against any liability, claims, demands, losses, damages, costs and expenses resulting from any of your acts, defaults or omissions and/or a breach of any warranty set forth herein. To the maximum extent permitted by law, you agree to defend, indemnify and hold harmless the Competition Entities from and against any and all claims, actions, suits or proceedings, as well as any and all losses, liabilities, damages, costs and expenses (including reasonable attorneys fees) arising out of or accruing from: (a) your Submission or other material uploaded or otherwise provided by you that infringes any third party proprietary rights, intellectual property rights, industrial property rights, personal or moral rights or any other rights, including without limitation, copyright, trademark, patent, trade secret, privacy, publicity or confidentiality obligations, or defames any person; (b) any misrepresentation made by you in connection with the Competition; (c) any non-compliance by you with these Rules or any applicable U.S. or foreign state or federal law; (d) claims brought by persons or entities other than the parties to these Rules arising from or related to your involvement with the Competition; and (e) your acceptance, possession, misuse or use of any Prize, or your participation in the Competition and any Competition-related activity.</h5>\nc. You hereby release Competition Entities from any liability associated with: (a) any malfunction or other problem with the Competition Website; (b) any error in the collection, processing, or retention of any Submission; or (c) any typographical or other error in the printing, offering or announcement of any Prize or winners.</h5>\n\n####15. INTERNET\na. Competition Entities are not responsible for any malfunction of the Competition Website or any late, lost, damaged, misdirected, incomplete, illegible, undeliverable, or destroyed Submissions or entry materials due to system errors, failed, incomplete or garbled computer or other telecommunication transmission malfunctions, hardware or software failures of any kind, lost or unavailable network connections, typographical or system/human errors and failures, technical malfunction(s) of any telephone network or lines, cable connections, satellite transmissions, servers or providers, or computer equipment, traffic congestion on the Internet or at the Competition Website, or any combination thereof, which may limit a Participant’s ability to participate.</h5>\n\n####16. RIGHT TO CANCEL, MODIFY OR DISQUALIFY\na. If for any reason the Competition is not capable of running as planned, including infection by computer virus, bugs, tampering, unauthorized intervention, fraud, technical failures, or any other causes which corrupt or affect the administration, security, fairness, integrity, or proper conduct of the Competition, Competition Sponsor reserves the right to cancel, terminate, modify or suspend the Competition. Competition Sponsor further reserves the right to disqualify any Participant who tampers with the submission process or any other part of the Competition or Competition Website.  Any attempt by a Participant to deliberately damage any website, including the Competition Website, or undermine the legitimate operation of the Competition is a violation of criminal and civil laws. Should such an attempt be made, Competition Sponsor and Kaggle each reserves the right to seek damages from any such Participant to the fullest extent of the applicable law.</h5>\n\n####17. NOT AN OFFER OR CONTRACT OF EMPLOYMENT\na. Under no circumstances will the entry of a Submission, the awarding of a Prize, or anything in these Rules be construed as an offer or contract of employment with Competition Sponsor or any of the Competition Entities. You acknowledge that you have submitted your Submission voluntarily and not in confidence or in trust. You acknowledge that no confidential, fiduciary, agency, employment or other similar relationship is created between you and Competition Sponsor or any of the Competition Entities by your acceptance of these Rules or your entry of your Submission.</h5>\n\n####18. DEFINITIONS\na. \"Competition Data\" are the data or datasets available from the Competition Website for the purpose of use in the Competition, including any prototype or executable code provided on the Competition Website. The Competition Data will contain private and public test sets. Which data belongs to which set will not be made available to Participants. </h5>\nb. An “Entry” is when a Participant has joined, signed up, or accepted the rules of a competition. Entry is required to make a Submission to a competition.</h5>\nc. A “Final Submission” is the Submission selected by the user, or automatically selected by Kaggle in the event not selected by the user, that is/are used for final placement on the competition leaderboard.</h5>\nd. A “Participant” or “Participant User” is an individual who participates in a competition by entering the competition and making a Submission.</h5>\ne. The “Private Leaderboard” is a ranked display of Participants’ Submission scores against the private test set. The Private Leaderboard determines the final standing in the competition.</h5>\nf. The “Public Leaderboard” is a ranked display of Participants’ Submission scores against a representative sample of the test data. This leaderboard is visible throughout the competition.</h5>\ng. A “Sponsor” is responsible for hosting the competition, which includes but is not limited to providing the data for the competition, determining winners, and enforcing competition rules.</h5>\nh. A “Submission” is anything provided by the Participant to the Sponsor to be evaluated for competition purposes and determine leaderboard position. A Submission may be made as a model, notebook, prediction file, or other format as determined by the Sponsor.</h5>\ni. A “Team” is one or more Participants participating together in a Kaggle competition, by officially merging together as a Team within the competition platform.</h5>\n\n  [1]: https://www.treasury.gov/resource-center/sanctions/Programs/Pages/Programs.aspx\n  [2]: http://www.kaggle.com/terms\n  [3]: http://www.opensource.org\n  [4]: http://www.opensource.org\n  [5]: https://www.kaggle.com/WinningModelDocumentationGuidelines\n  [6]: http://www.kaggle.com/privacy\n  [7]: http://www.kaggle.com/contact\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}