Xente Fraud Detection Challenge
$4,500 USD
Accurately classify the fraudulent transactions from Xente's e-commerce platform
20 May–22 September 2019 23:59
1027 data scientists enrolled, 508 on the leaderboard
Product Category Discrepancy
published 8 Jul 2019, 17:30

Any ideas on how to handle the inclusion of an additional category whereas its not present in the training dataset? I thought of including the category as part of 'other' but its not working pretty well.

You can combine train and test datasets , generate dummies and split them back in their usual form.

Interesting ... thanks for that advise