{
  "fetched_at": "2026-10-19T17:03:56Z",
  "source_url": "https://www.kaggle.com/competitions/global-dengue-outbreak-prediction-challenge/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The dataset provided for the **Global Dengue Outbreak Prediction Challenge** is a compilation of individual health records, designed to facilitate the development of machine learning models to predict dengue fever diagnosis. Each record contains a set of symptoms commonly associated with dengue and a binary label indicating whether the individual was diagnosed with the disease.\n\nBelow is the structure of the dataset along with a brief description of each field:\n\n- `Name`: The individual's name. This is a nominal variable used for identification purposes.\n- `Fever`: Binary indicator of the presence of fever (1 for present, 0 for absent).\n- `Headache`: Binary indicator of the presence of headache (1 for present, 0 for absent).\n- `JointPain`: Binary indicator of the presence of joint pain (1 for present, 0 for absent).\n- `Bleeding`: Binary indicator of the presence of bleeding (1 for present, 0 for absent).\n- `Dengue`: Binary label indicating whether the individual was diagnosed with dengue (1 for positive diagnosis, 0 for negative diagnosis).\n\nHere is an example of how the data appears:\n\n```\nName,Fever,Headache,JointPain,Bleeding,Dengue\nJeremy Long,0,0,1,1,1\nCassandra Glover,1,1,1,0,1\nAaron Adams MD,0,1,1,0,0\nElizabeth Thomas,0,1,0,1,1\nMathew Perez,0,0,1,0,1\nJordan Andrews,0,1,1,1,0\nMike Cruz,0,0,1,0,0\n```\n\n## Important Notes:\n\n- The dataset is anonymized, with any personally identifiable information removed.\n- The dataset contains both symptomatic cases and controls to help with the identification of patterns.\n- Participants are encouraged to explore feature engineering opportunities to improve their model's predictive power.\n- The dataset is balanced with respect to the target variable to prevent model bias toward a particular outcome.\n\nParticipants should use this dataset to train their models to predict the 'Dengue' variable. The quality of the predictions will be evaluated based on the evaluation metric detailed on the competition's evaluation page.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Welcome to the **Global Dengue Outbreak Prediction Challenge**. This competition seeks to leverage the power of data science to predict dengue outbreaks across the globe. Dengue fever, caused by the dengue virus and transmitted by mosquitoes, poses a significant public health challenge in tropical and subtropical regions worldwide.\n\nIn this challenge, participants will develop machine learning models to identify patterns and predict future dengue outbreaks based on a comprehensive dataset, including weather patterns, population density, historical dengue incidence rates, and other environmental factors.\n\n## The Problem\n\nThe primary goal of this competition is to predict the occurrence and intensity of dengue outbreaks in different geographical locations. Accurate predictions can help healthcare providers and policymakers deploy resources more effectively to prevent and combat the spread of this disease.\n\nParticipants are expected to submit a model that can accurately forecast the number of dengue cases for given time periods and locations. Submissions will be evaluated based on a specific metric that balances precision and recall, ensuring that the predictions are both accurate and relevant.\n\n## Data Description\n\nThe dataset provided includes the following features:\n\n- Historical dengue incidence rates by region.\n- Climate variables such as temperature, humidity, and rainfall.\n- Socioeconomic data, including population density and urbanization rates.\n\nParticipants should use this data to train their models, adhering to the competition rules and respecting the ethical guidelines of data usage.\n\n## Submission Guidelines\n\n`Submissions` should be formatted as specified in the data description page. Each submission will be evaluated automatically against the hidden test set, and participants will receive immediate feedback on the leaderboard.\n\n## Evaluation Metric\n\n```\n# The evaluation metric for this competition is the F1 Score\nfrom sklearn.metrics import f1_score\ny_true = [0, 1, 1, 0, 1, 0]\ny_pred = [0, 1, 0, 0, 1, 1]\nscore = f1_score(y_true, y_pred, average='binary')\nprint('F1 Score:', score)\n```\n\n## LaTeX Equations\n\nParticipants may find it useful to employ statistical models or algorithms within their submissions. For example, the equilibrium of a basic SIR model in epidemiology can be represented by the following equation:\n\n$$ R_0 = \\frac{\\beta}{\\gamma} $$\n\nHere, \\( R_0 \\) is the basic reproduction number, \\( \\beta \\) is the transmission rate, and \\( \\gamma \\) is the recovery rate.\n\n## Join the Challenge\n\nJoin us in this important endeavor to apply your data science expertise to a real-world problem with far-reaching impact. Help us make strides in predicting and preventing dengue fever outbreaks and improve public health outcomes worldwide.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "**Evaluation**:\n\nThe evaluation criteria for the **Global Dengue Outbreak Prediction Challenge** are designed to measure how well the participants' models predict the number of dengue cases. The goal is to minimize the error between the predicted values and the actual number of cases.\n\nSubmissions will be evaluated using the **Mean Absolute Error (MAE)**. MAE is a risk metric corresponding to the expected value of the absolute error loss or \\( l1 \\)-norm loss.\n\n$$ \\text{MAE} = \\frac{\\sum_{i=1}^{n} |y_i - \\hat{y}_i|}{n} $$\n\n******Where******:\n- \\( y_i \\) is the actual number of dengue cases,\n- \\( \\hat{y}_i \\) is the predicted number of cases,\n- \\( n \\) is the number of observations in the test set.\n\nThe MAE reflects the average magnitude of the errors in a set of predictions, without considering their direction. It’s particularly useful in this competition because it quantifies the accuracy of predictions regardless of whether the predicted values are over or under-estimates.\n\n---\n\n## Submission File\n\nParticipants must submit their predictions in a `submission.csv` CSV file with a header. For each observation in the test set, participants will provide an ID and their predicted count of dengue cases. The file should have the following format:\n\n```\nID,PredictedCases\n1,12\n2,5\n3,8\netc.\n```\n\nAll submissions should be evaluated by the competition’s automated system, and results will be reflected on the leaderboard. Ensure that the submissions are in the correct format to avoid any disqualification or incorrect scoring.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "# Competition Rules: Restrictions\n\n## Data Use\n- The competition dataset **must not be used** for any purpose outside of this competition.\n- **Commercial use** of the data is strictly prohibited.\n\n## Submissions\n- **Automated submissions** through scripts or bots are not permitted.\n- **Manual re-submission** of other participants' predictions is prohibited.\n\n## Model Requirements\n- The use of **external data** not provided by the competition is not allowed unless explicitly permitted.\n- **Proprietary or licensed software** with restrictions on free public use cannot be used to develop models.\n\n## Collaboration\n- **Collusion** between participants to share solutions or manipulate rankings is strictly forbidden.\n- **Multiple accounts** per participant or team are not allowed and will lead to disqualification.\n\n## Ethical Standards\n- Participants must not engage in any activities that may give them an unfair advantage.\n- **Reverse engineering** of the scoring algorithm or any other kind of **hacking** into the Kaggle system is prohibited.\n\n## Intellectual Property\n- Submissions must be the original work of the participants, and any form of **plagiarism** will result in disqualification.\n\n## Prize Eligibility\n- Failure to comply with the verification process for winner selection will result in forfeiture of the prize.\n- Participants from countries under **US export sanctions** or countries where local laws prohibit participation are not eligible for prizes.\n\n## Fair Play\n- Any behavior intended to **disrupt** the fair play of the competition is not allowed.\n- Participants must not use means to **artificially boost or alter** the competition’s rankings, like submitting misleading or false information.\n\n## Compliance\n- Participants found to be in **violation of any rule** may be subject to disqualification, prize forfeiture, and/or legal action.\n\n*Note: These rules are subject to change. Participants will be notified of any changes. It is the responsibility of participants to stay informed about the competition rules.*\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "# Global Dengue Outbreak Prediction Challenge\n\n## Description\n\nWelcome to the **Global Dengue Outbreak Prediction Challenge**. In this competition, you are invited to create innovative machine learning models that can predict dengue fever outbreaks. Your models will assist public health authorities in making informed decisions for better planning and resource allocation to prevent the spread of this disease.\n\n## Objective\n\n- **Predict dengue fever outbreaks**: Use environmental and population data to forecast the occurrence of dengue in multiple regions.\n- **Support public health efforts**: Provide actionable insights that can be used to mitigate the impact of dengue fever.\n\n## Fields in the Dataset\n\n- `Name`: The name of the individual (String).\n- `Fever`: Presence of fever (1 for yes, 0 for no).\n- `Headache`: Presence of headache (1 for yes, 0 for no).\n- `JointPain`: Presence of joint pain (1 for yes, 0 for no).\n- `Bleeding`: Presence of bleeding (1 for yes, 0 for no).\n- `Dengue`: Diagnosis of dengue (1 for positive, 0 for negative).\n\n## Evaluation\n\n- The primary metric for this competition will be the **Mean Absolute Error (MAE)** between the predicted number of cases and the actual recorded data.\n- Detailed evaluation criteria will be provided on the competition's webpage.\n\n## Prizes\n\n- Prizes for the top competitors will be announced subject to Kaggle's competition prize guidelines and approval.\n\n## Terms and Conditions\n\n- By participating in this competition, you agree to Kaggle's terms and conditions.\n- Please ensure that any cash prizes comply with Kaggle's policies and have received prior approval.\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}