Skip to content

kapedalex/Client_default_prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Client_default_prediction

This project aims to analyze client behavior and predict the likelihood of defaulting on loans using machine learning techniques. The analysis leverages various client characteristics and payment history to segment clients and evaluate their risk profiles.

Objectives

  • Client Segmentation: Identify client segments with a default rate of less than 25%.
  • Data Analysis: Analyze payment data to understand default trends and revenue.
  • Model Training: Build a predictive model using the CatBoost algorithm to classify clients based on the risk of default.

Data Sources

  • Anket.csv: Contains client demographic information.
  • Payments.csv: Contains payment history and amounts.
  • ML.csv: Contains additional features for model training.

How to Use

  • Execute the Code: Run the provided code in your Python environment.
  • Interpret the Results: The code produces visualizations that illustrate the efficient frontier, Capital Market Line, and optimal portfolios according to various criteria.
  • Customize and Explore: You can modify the assets, optimization parameters, and constraints to experiment with different scenarios and preferences.

TODO

  • Implement additional feature selection techniques.
  • Explore other machine learning algorithms for comparison.

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published