Financial Institutions are in the business of giving out loans to customers. These lenders use various factors such as but not limited to the loan amount approved, credit score, income, debt-to-income ratio, loan tenure, Central bank rates, prime rate (the lowest possible interest rate at which financial institutions can lend money to their most trustworthy customers), number of products utilized, number of accounts, etc. to determine the appropriate interest rate for each customer.
Assessing customer risk profiles to determine the required interest rate has been a standard practice for lenders. But instead of an experienced person making credit decisions, can machine learning be used to learn from the historical good and bad decisions to make reliable credit decisions in the future?
This project was for me to kick-start my machine learning training and also demonstrate how easy it is to create a solution.
Fig1: Raw data downloaded from Kaggle uploaded as a .csv file in mlOS.
To have a model that can predict at over 96% accuracy was great. Imagine the advantage that lenders could have!
Fig2: Compare Predicted vs Original interest rates
Once the model was built, it was deployed to production as a real-time app named RiskPrice_App. It automatically created an Application Programming Interface (API) that can now be called from any application in the world. The Dashboard was automatically created and RiskPrice_App can be accessed.
Fig.3: Run the App from the dashboard and click “Predict”.
In this case, based on the inputs provided, the estimated interest rate for this customer is predicted to be 11.28.
Developers can develop an application to interface with models for use in their corporate businesses. A benefit to both potential borrowers and lenders is to know the importance of factors used to determine the interest rates so that they can increase their creditworthiness by placing themselves in a better position to negotiate appropriate interest rates.
Silas Adiko has prior experience in Oracle database administration and applications support in both consultancy and banking industries. He has a B.Sc. in Computer Science and Statistics and an M.Sc. in Actuarial Science. He’s always intrigued and passionate about predictive analytics and hopes to actualize this desire through Machine Learning. Silas is on a mission to apply the wealth of knowledge to advance society and his career.