# Volunteer Future Collaboration Prediction — Data

来源：https://www.kaggle.com/competitions/MLSP2023-volunteers-part2/data

采集时间：2026-10-19T11:47:47Z

## Files
*   **colab_train.csv** - Training dataset, containing records of train volunteers participating in tasks during **feature time span** (2020.2-2021.8). Details of the columns can be found in the next session.
*   **colab_train_edge_list.csv** - A graph of volunteers derived from the collaboration in the **colab_train.csv**. Nodes are volunteers, edges denote the collaboration between two volunteers, and edge weights represent the count of collaboration between two volunteers.
*   **colab_test.csv** - Testing feature dataset, containing records of test volunteers participating in tasks during **feature time span** (2020.2-2021.8).
*   **colab_test_candidate_multistep.csv** - This file contains all candidate links to predict. Each `Id` identifies a link, and it's the join of two volunteer IDs with an integer from 0 to 5 representing the timestamp. The 0-5 timestamp corresponds to each month in the **predict time span** (2021.8 - 2022.1).  For example, `13-141-0` means the edge between volunteer 13 and 141, at time step 0 (2021.8). `141-127469-1` means the edge between volunteer 141 and 127469 at time step 1 (2021.9).  Competitors should predict whether each edge will exist and output to a column `Predicted`, both probs or binary outputs (0,1) are acceptable.
*   **sample_submission_collaboration_multistep.csv** - A submission sample with correct format.

## Columns

*   `user_id` - The unique id of a volunteer
*   `is_organizer` -  Whether the volunteer is the organizer of the task (binary)
*   `task_id` -The unique id of a task
*   `task_location` - The street name of the task location (text)
*   `task_district` - The district name of the task location (text)
*   `user_location` - The home address of the volunteer (text)
*   `longitude` - The longitude of the task location
*   `latitude` - The latitude of the task location
*   `task_start_time` - The start time of the task
*   `task_end_time` - The end time of the task
*   `node1` - Unique ID of volunteer A
*   `node2` - Unique ID of volunteer B
*   `weight` - Collaboration times between volunteer A and volunteer B