Financial Institution need an effective way to evaluate customers creditworthiness to minimize loan and default risk . The goal of this project is to calculate the credit score based on key financial indications and segment customers into different categories.
Python Pandas,Numpy,Plotty,Scikit-Learn,K-Means Clustering
1.Used a dataset containing customer details like Payment history ,Credit utilization ratio ,loan amount, intrest rate , employment status.
2.Implemented a weighted formula inspired by FICO scoring model to assign credit scores based on key functional features.
3.Applied k-means clustering algorithm to group customer into four categories : Very low, Low ,Good,Excellent .
4.Used Plotty to analyze the distribution of credit utilization ,loan amounts and correlation between financial factors.
5.Successfully build credit scorig model that helps predict the creditworthiness of individuals segment customer into four risk categories to help financial institutions make better loan decisions. Acheived an interpretable model that provide actionable insights for lenders to minimize credit risk.