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
- joblib
- numpy
- python
- scikit-learn
Log in or sign up for Devpost to join the conversation.