What it does

Analyzes each variable of the Singlife dataset and attempts to predict whether a client is likely to quit out of purchasing policies early.

How we built it

Quickly, and scrappily.

Challenges we ran into

The time constraints and the fact that we couldn't meet up together throughout the datathon.

What we learned

Basics of SMOTE, scikit, pandas for data processing, etc.

What's next for Singlife, not Shaglife

  • Improving and testing various models for different parameter types such as decision trees.
  • Enhancing data processing pipeline, by incorporating methods such as PCA

Built With

Share this project:

Updates