{
  "fetched_at": "2026-10-19T08:39:09Z",
  "source_url": "https://www.kaggle.com/competitions/MLSP2023-volunteers-01/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Here are datasets for the volunteer retention prediction tasks:\n\n#Retention Task\n## Files\n\n*   **retention_train_feat.csv** - the training dataset, containing records of train volunteers participating in tasks during the **feature time span** (2020.2-2021.5). Details of each record can be found in the following session.\n*   **retention_test_feat.csv** - the testing dataset.\n*   **sample_submission_retention.csv** - a sample submission file in the correct format\n*   **retention_gt_train.csv** - the groudtruth labels for each volunteer in the training dataset. `user_id` denotes the unique id of a volunteer, and the `count` is the label for that volunteer, representing the count of participated tasks in the **predicted time span** (2021.5 - 2022.2).  \n\n## Columns\n\n*   `user_id` - The unique id of a volunteer\n*   `is_organizer` -  Whether the volunteer is the organizer of the task (binary)\n*   `task_id` -The unique id of a task\n*   `task_location` - The street name of the task location (text)\n*   `task_district` - The district name of the task location (text)\n*   `user_location` - The home street name of the user (text)\n*   `longitude` - The longitude of the task location\n*   `latitude` - The latitude of the task location\n*   `task_start_time` - The start time of the task\n*   `task_end_time` - The end time of the task\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "# Announcement💥\n## [2023.07.15] New Dates for Paper Submission\nDear Participants，here are some updates on the evaluation and paper submission process of this challenge:\n1. Challenge Winner and Paper Selection Rules:\n🚩:Winners will be selected according to the best performance for each single task, separately.  Therefore, one winner for each task will be selected.\n🚩:Up to four papers will be accepted to be presented at the conference.\n🚩:Papers will be peer reviewed as in a regular conference submission. They will be scored based on their model performance on the private test data (75%) and paper quality (25%). Paper quality metrics include clarity of method, correctness, reproducibility and originality (bonus).\n2. Paper Summary Submission:\n🚩:Submit a one-page summary about your methodology and numerical results by **July 20th**.\n🚩:Please follow the paper submission instructions on MLSP website. Make sure to choose the track **“MLSP2023 - Data Competition Papers” on CMT**.\n🚩:If you have already finished writing the paper, you can use it instead of the summary.\n🚩:You must submit the initial summary to be eligible for the final paper submission.\n3. Final Paper Submission:\n🚩:You can upload the full version of your paper to the paper submission system before the final submission deadline.\n🚩:The final paper deadline is **July 27th**.\n\n# About this Task👀\nRecent years have seen a rise in online crowdsourcing platforms that facilitate volunteering efforts, allowing individuals to contribute to collective goals and address community needs. To optimize these efforts, it is crucial to understand volunteer behavior and collaboration patterns. In this challenge, we present a volunteer participation dataset with two tasks:\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F9176866%2F03e5406fa4ebf49cc9ad51542896e7dc%2Fslide8(1).gif?generation=1687098246971184&alt=media)\n\nVolunteer Dataset: The dataset is collected from a mobile crowdsourcing app called “Anti-Pandemic Pioneer” used for organizing volunteers during the COVID-19 pandemics in Shenzhen, China. It contains records of each volunteer participating in a task, including features like volunteer ID, task ID, timestamp, task location, etc. Task names and descriptions will also be provided.\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F9176866%2F95e49f9816dd5fd63af1987ab3297717%2Fmap.png?generation=1687256611473169&alt=media)\n\n**Task 1: Retention Prediction:** As indicated by the orange highlighted area in the above figure, the dataset used in the retention prediction task encompasses all districts in Shenzhen. Participants are given a dataset consisting of volunteers and their participation histories from February 2020 to May 2021. The goal is to predict the retention of each volunteer, which is defined as the number of future participations during the prediction time span from May 2021 to February 2022. The ground truths for evaluation are determined by counting the number of tasks in which each user participated during the prediction time span.\n\n**Key Points & Competition Details:**\n- Participants can choose to participate in either one or both tasks.\n- The datasets for both tasks have identical structure but sampled from distinct districts, ensuring no overlap.\n- The evaluation metrics are Root Mean Squared Error(RMSE) for Task 1 and Area Under Receiver Operating Characteristic curve (AUC-ROC) for Task 2.\n- Both datasets are split into a train set and a test set. The test sets are further split into private test set (2/3 for final evaluation) and public test set (1/3 for getting feedbacks during the competition).\n- Participants can access all datasets but only labels for the train sets.\n- Submissions can be made for the public test set twice a day, and immediate scores (RMSE and AUC-ROC) will be provided.\n- Submission deadline will be one months after the start of the competition.\n\n**If you have any questions or inquiries regarding this competition, please do not hesitate to contact us. You can reach out to us through [our Slack channel](https://join.slack.com/t/volunteer-challenge/shared_invite/zt-1xq09saep-50EqZDlw7ds5EHN3Lbp1_g).**\n\n**To access further details about the competition, please visit our [competition website](https://volunteerchallenge.github.io/).**\n\n**Please NOTE.** that the intellectual property (IP) is not transferred to the challenge organizers, i.e., if code is shared/submitted, the participants remain the owners of their code (when the code is made publicly available, an appropriate license should be added).\n\n**Privacy Notice.** The volunteer activity data used in this challenge were passively collected from the mobile platform with personal identification information removed. No investigations on humans were involved. During the preparation of this challenge, the organizers did not have access to any identification information associated with the collected data. We are committed to adhering to strict privacy and ethical guidelines during the entire competition process.\n\n**Acknowledgement.** We thank the Shenzhen Pioneers APP operation team for providing the volunteer data.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "**Please NOTE.** that the intellectual property (IP) is not transferred to the challenge organizers, i.e., if code is shared/submitted, the participants remain the owners of their code (when the code is made publicly available, an appropriate license should be added).\n\n**Privacy Notice.** The volunteer activity data used in this challenge was passively collected from the mobile platform with personal identification information removed. No investigations on humans were involved. During the preparation of this challenge, the organizers did not have access to any identification information associated with the collected data. We are committed to adhering to strict privacy and ethical guidelines during the entire competition process.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The goal of this task is to predict the retention of each volunteer, which is defined as the number of future participations during the prediction time span from May 2021 to February 2022. \n\n## Submission Format\n\nPlease ensure that your submission files adhere to the following format requirements:\n\n- The files should have two columns named `Id` and `Predicted`.\n- The `Id` column should consist of integers representing the unique ID of each participant.\n- Each `Predicted` value in the file represents the predicted number of times the corresponding participant will volunteer.\n\nThe file should contain a header and have the following format. Also, a submission sample is given at the [Data](https://www.kaggle.com/competitions/MLSP2023-volunteers-01/data?select=sample_submission_retention.csv) page\n```\nId,Predicted\n186335,3\n148229,9\n\n```\n\n## Root Mean Square Error (RMSE)\n\n\nThe evaluation metric for this competition is [The root mean square error (RMSE)](https://en.wikipedia.org/wiki/Root-mean-square_deviation). The RMSE usually measures the average difference between a statistical model's predicted values and the actual values. It provides a quantitative measure of the accuracy of a regression model.\n\nRMSE is particularly useful when the magnitude of errors needs to be emphasized, as it penalizes larger errors more severely than [mean absolute error (MAE)](https://en.wikipedia.org/wiki/Mean_absolute_error).\n\n### Formula\n\nThe RMSE is calculated using the following formula:\n\n![RMSE Formula](https://latex.codecogs.com/svg.latex?%5Cdpi%7B120%7D%20RMSE%20%3D%20%5Csqrt%7B%5Cfrac%7B%5Csum_%7Bi%3D1%7D%5E%7Bn%7D%28y_i%20-%20%5Chat%7By_i%7D%29%5E2%7D%7Bn%7D%7D)\n\nwhere:\n- ![y_i](https://latex.codecogs.com/svg.latex?%5Cdpi%7B120%7D%20y_i) represents the actual value of the target variable for the i-th observation.\n- ![y_hat_i](https://latex.codecogs.com/svg.latex?%5Cdpi%7B120%7D%20%5Chat%7By_i%7D) represents the predicted value of the target variable for the i-th observation.\n- n is the total number of observations.\n\nRMSE is always non-negative, and a value of 0 (almost never achieved in practice) would indicate a perfect fit to the data. In general, a lower RMSE is better than a higher one. However, comparisons across different types of data would be invalid because the measure is dependent on the scale of the numbers used.\n\n\n\n\n\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Timeline",
      "content": "Important Dates:\n- Jul 19, 2023: Deadline for Submitting Results\n- Jul 20, 2023: Paper Summary Submission\n- Jul 27, 2023: Final Paper Submission\n- Aug 15, 2023: Notification of paper acceptance\n- Aug 25, 2023: Camera-Ready Challenge Papers Deadline",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Announcement",
      "content": "# Announcement💥\n## [2023.07.15] New Dates for Paper Submission\nDear Participants，here are some updates on the evaluation and paper submission process of this challenge:\n1. Challenge Winner and Paper Selection Rules:\n🚩:Winners will be selected according to the best performance for each single task, separately.  Therefore, one winner for each task will be selected.\n🚩:Up to four papers will be accepted to be presented at the conference.\n🚩:Papers will be peer reviewed as in a regular conference submission. They will be scored based on their model performance on the private test data (75%) and paper quality (25%). Paper quality metrics include clarity of method, correctness, reproducibility and originality (bonus).\n2. Paper Summary Submission:\n🚩:Submit a one-page summary about your methodology and numerical results by **July 20th**.\n🚩:Please follow the paper submission instructions on MLSP website. Make sure to choose the track **“MLSP2023 - Data Competition Papers” on CMT**.\n🚩:If you have already finished writing the paper, you can use it instead of the summary.\n🚩:You must submit the initial summary to be eligible for the final paper submission.\n3. Final Paper Submission:\n🚩:You can upload the full version of your paper to the paper submission system before the final submission deadline.\n🚩:The final paper deadline is **July 27th**.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}