Credit Risk Evaluation

The following goals were achieved:

- Determine the correlations with whether or not credit was granted.

- Develop a credit scoring prediction model.

- Create an interactive dashboard via Power BI to visualize the model results.

The following tasks were completed:

- Download the dataset from Kaggle using this link: https://www.kaggle.com/datasets/kabure/german-credit-data-with-risk?resource=download.

- Import the dataset to the SQL Server database to clean it.

- Clean and transform the data to prepare it for analysis.

- Import the dataset to Power BI to perform the analysis.

- Analyze data in Power BI.

- Visualize data in Power BI and create an interactive dashboard.

- Deliver insights from the analysis and provide recommendations to enhance credit risk assessment.

The following tools were used:

- Microsoft SQL Server to clean the data.

- Power BI to analyze the data and build the dashboard.

This project analyzed the credit scoring dataset. The dashboard revealed that a large portion of loans are issued to younger borrowers (20–40 years old) with minimal financial reserves and are concentrated in car-related purposes. While most borrowers fall under the "good risk" category, a significant proportion are still high-risk borrowers. To improve credit portfolio stability:

- Diversify loan purposes

- Implement risk-based loan policies

- Encourage savings-linked borrowing practices

By addressing these areas, the organization can better manage credit risk and optimize loan performance for long-term sustainability.