UmojaHack #2: Xente Purchase Prediction Challenge (INTERMEDIATE) by UmojaHack Africa
$600 USD
Predict when and what a customer will purchase on the Xente app
385 data scientists enrolled, 40 on the leaderboard
Financial ServicesForecastStructured
Africa
21 March 09:00 (8 hours)

The training data consists of individual transaction records. Each row contains an account ID (‘acc’), the time and date of the transaction (‘date’) and the product ID (‘PID’). Products can fall into several categories, as described in PID_Categories.csv. The training data covers the period from 2019-11-01 to 2020-02-23. SampleSubmission.csv shows the desired format for your predictions, covering the week beginning on 2020-02-23. Note that the sample submission file only includes rows for accounts that transacted during that time period - please ensure your submission matches the sample submission, with one row for each account for each day for each product.

In order to make access to the data easier for all participants, we have provided download links. We recommend you download the data before the challenge. The data is password protected, and we will share the password to all universities as well as on the livestream when the competition opens.

Folder codes will be shared on the day at 09:00 GMT on the University rep WhatsApp groups.

The following files are available for download:

  • Train.csv - is the dataset that you will use to train your model. It contains all transactions during the training period
  • SampleSubmission.csv - is an example of what your submission file should look like. The order of the rows does not matter, but the names of the IDs(Account X date X PID) must be correct.
  • PID_Categories.csv - The categories to which the various products belong