Skip to content

Implementing segmentation and churn prediction with time series of transaction data.

Notifications You must be signed in to change notification settings

neojohny/TS_challenge

Repository files navigation

TS_challenge

In this project, a two-year transaction history data from merchant was given to achieve two goals. The first is merchant segmentation and the second is customer churn prediction.

Feature Engineering

  • TSFresh
  • Experience

Clustering

  • visualization
  • Hyper-parameter tuning
  • Center explain

Churn Definition and Identify

  • Empirical and Theoretical

Supervised Learning to Predict Churn

  • Model selection
  • HP tuning
  • Reasoning for churn
  • Approach to handle the churn

=============================================

Lesson learnt: read the question carefully. if they want to present to business, then no need for technical details.

About

Implementing segmentation and churn prediction with time series of transaction data.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published