Subscribe to DSC Newsletter

Multinomial Logistic Regression Predicting Cluster Membership


I recently developed a cross sell application that took product purchase history and flagged the record with a 1 for purchased, and 0 if not, within orders. 

I then used Multinomial Logistic Regression to assign new orders to the cluster. 

I found that at a certain point, the classification did not work with too many clusters, but was flawless with fewer clusters @ 100% correct classification. 

The goal was to produce cross sell tables and rates according to the cluster membership as opposed to one single table. 

This may seem like a lot of effort but then I put the whole thing into a spreadsheet application that call center reps could use while talking with customers who were buying. 

The reason I did this, was because they had not solutions for this and none are in sight. 

Anyway, what could I have done better in this situation?



Views: 4649

Reply to This

Replies to This Discussion

Can you pop it into a VBA package in little to no time? If so, I need a tutorial on that.

If you havent't already done so you should think about using Association Analysis (Market Basket Analysis) to identify combinations of products that go well together. This might be an interesting alternative to Cluster Analysis and a Regression Model.The combinations of products you derive can also be exported to an Excel spreadsheet.

Association Analysis is implemented in products like R or RapidMiner which are open source and will help you to keep costs for implementation low.


On Data Science Central

© 2020   TechTarget, Inc.   Powered by

Badges  |  Report an Issue  |  Privacy Policy  |  Terms of Service