{
  "fetched_at": "2026-10-19T14:09:30Z",
  "source_url": "https://www.kaggle.com/competitions/cassandra23-ps-2/data",
  "pages": [
    {
      "name": "data-description",
      "content": "The task is to predict the time taken to complete a delivery given the details of an order. \nYou have been given a training dataset that contains the detials of the order and time taken to complete the delivery, and a testing dataset that contains the details of the order but not the time taken to complete the delivery. Use the training dataset to build a Machine Learning model that can predict the `actual_time` variable given other variables. \n\nMake predictions using your ML model on the testing dataset and submit a csv file that contains the time taken to complete the deliveries in testing dataset mapped against the unique identifiers (UID). Check out `sample_submissions.csv` to understand the submission format.\n\n\n## Files\n\n*   **train_data.csv** - the training set\n*   **test_data.csv** - the test set\n*   **sample_submissions.csv** - a sample submission file in the correct format\n\n## Columns\n\n* `UID` : Unique IDentifier used to identify each unique sample in the dataset\n* `trip_creation_time` : Timestamp of trip creation\n* `route_schedule_uuid` : Unique Id for a particular route schedule\n* `route_type` – Transportation type\n* `FTL – Full Truck Load` : FTL shipments get to the destination sooner, as the truck is making no other * pickups or drop-offs along the way\n* `Carting`: Handling system consisting of small vehicles (carts)\n* `trip_uuid` : Unique ID given to a particular trip (A trip may include different source and destination centers)\n* `source_center` : Source ID of trip origin\n* `source_name` : Source Name of trip origin\n* `destination_cente` : Destination ID\n* `destination_name` : Destination Name\n* `od_start_time`: Trip start time\n* `od_end_time` : Trip end time\n* `start_scan_to_end_scan` : Time taken to deliver from source to destination\n* `is_cutoff` : Unknown field\n* `cutoff_factor` : Unknown field\n* `cutoff_timestamp` : Unknown field\n* `actual_distance_to_destination` : Distance in Kms between source and destination warehouse\n* `osrm_time` : An open-source routing engine time calculator which computes the shortest path between points in a given map (Includes usual traffic, distance through major and minor roads) and gives the time (Cumulative)\n* `osrm_distance` : An open-source routing engine which computes the shortest path between points in a given map (Includes usual traffic, distance through major and minor roads) (Cumulative)\n* `factor` : Unknown field\n* `segment_actual_time` : This is a segment time. Time taken by the subset of the package delivery\n* `segment_osrm_time` : This is the OSRM segment time. Time taken by the subset of the package delivery\n* `segment_osrm_distance` : This is the OSRM distance. Distance covered by subset of the package delivery\n* `segment_factor` : Unknown field\n* `actual_time` : Actual time taken to complete the delivery (Cumulative)",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "## About Udyam\n\nUdyam is the Annual Technological Festival of the department of Electronics Engineering, IIT (BHU) Varanasi. It brings a broad spectrum of events spanning Data Science, Machine Learning, Digital and Analog Electronics and others to boost the participant's skill sets. Since 2010, Udyam has provided a platform to develop and showcase the technical skills of Indian technocrats. And we are pleased to announce that the grand event is again returning this spring as UDYAM'23!\n\n\n## About Cassandra\n\nCassandra is the Data Science event organised under Udyam. Prove yourself a good data analyst by designing a model that learns and optimizes the dataset provided, implementing Machine Learning algorithms in industrial problems and gain exposure to the ABCs of data science.\n\n**NOTE: To participate in this competition, your team must be registered on [Udyam-EES](https://eesiitbhu.in/udyam).**\n\n## Problem Statement\n\nYou work as a Data Scientist at your friend's start-up named Smart Kashi Transport Services, which offers end to end delivery services to clients accross India. A crucial problem in delivery services is to predict the time required to deliver the goods from pickup point to destination. Your job is to build a Machine Learning Model that can predict the time taken to deliver a product, given all the details of the job. Check out Data section for elaboration. \nNote: Violation of any Kaggle Community Guidelines will lead to immediate disqualification of the respective team.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "- Team size: Minimum 1 and Maximum 3.\n- Refrain from plagiarising code from your fellow participants, this will lead to immediate disqualification.\n- Use of the external datasets is not allowed.\n- Event organizers will have a final say over the rules, usage of unethical means will lead to penalty or disqualification.\n- Teams that are not registered on [**Udyam-EES website**](https://eesiitbhu.in/udyam) will not be considered for further rounds and prizes.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "The submissions are evaluated using **Root Mean Squared Error (RMSE)**.\n\nLet Tᵢ be the time taken to complete a delivery and T'ᵢ be the predicted time to complete the ith delivery, then:\n\n\n![](https://www.googleapis.com/download/storage/v1/b/kaggle-user-content/o/inbox%2F7145153%2F0617ed6e962f2d920c948b0d527b05e4%2Fmath-20230326.png?generation=1679826104631282&alt=media)\n",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}