Banking Risk Analytics Dashboard

Problem Statement

Banks and financial institutions face the challenge of assessing whether applicants will default on their loans. Poor lending decisions increase non-performing loans (NPLs) and financial losses. This project explores how exploratory data analysis (EDA) and visualization can reveal patterns in applicant profiles that drive credit risk.

Solution

• Performed EDA on loan applicant data to identify key factors influencing default risk, such as:
  • Age
  • Income
  • Employment history
  • Loan amount
  • Credit history
• Built interactive Power BI dashboards that allow risk officers to:
  • Compare profiles of defaulters vs. non-defaulters.
  • Track portfolio-level risk indicators (default % by income band, loan purpose, credit score).
  • Make data-informed decisions when evaluating loan applications.

This approach provides managers with a transparent view of lending risk before implementing predictive models.

Installation

git clone https://github.com/emmanuel-ocran/banking-risk-analytics-dashboard.git
cd banking-risk-analytics-dashboard