I want to predict the user to buy or not a product in next month in the e-comercial site. I mainly using the past 1-year data to predict it. But I found the training data is imbalanced, and the buy(1)users is just 15% of all users, and buy(1) is just 8% in the test data. How to deal with this issue about time-series imbalance classification data.
$\begingroup$
$\endgroup$
Add a comment
|