DATA MINING CUP 2010

Scenario

Many customers only make an order in an online shop once. There are many reasons why they do not make another order. Online dealers try to counteract this using appropriate customer loyalty measures. For example, a tried-and-tested method is to hand out vouchers some time after an order to encourage the customer to make a follow-on purchase. But from an economic perspective sending vouchers to all customers is not a good solution because customers may make a second purchase without the incentive.With this scenario in mind, a media dealer has set the task for this year’s DMC. In addition to such classical media as books and CDs, the dealer offers in its online and normal shops a variety of book types such as audio book downloads, ebooks and ebook readers. Those customers that could be encouraged to buy again with a voucher are to be identified. This scenario assumes that a follow-on purchase is desired within 90 days of the initial order.

Task

Using the existing characteristics of a customer’s initial order, such as order quantity per type of goods, title and delivery weight, a decision must be made on whether to send a voucher worth € 5.00. The customers who receive a voucher should be those who would not have decided to re-order by themselves.

Downloads

Task
Solution

Winners

1st Place:

Team 2 Karlsruhe Institute of Technology

Winning team of DATA MINING CUP 2010

2nd Place:

Team 2 Universität Dortmund

3rd Place:

Team 1 Karlsruhe Institute of Technology

© 2022 GK Artificial Intelligence for Retail AG