This project performs exploratory data analysis (EDA) on a banking customer transaction dataset using Python. The analysis focuses on customer transactions, credit ratings, risk scores, transaction behavior, regional performance, product popularity, and managerial performance to uncover meaningful business insights.
Using Python libraries such as Pandas, NumPy, and Matplotlib, the project demonstrates data cleaning, statistical analysis, aggregation, and visualization techniques commonly used in financial analytics.
- Perform exploratory data analysis on banking transaction data
- Analyze customer transaction behavior
- Study credit score and risk score distributions
- Compare credit and debit transactions
- Identify regional transaction trends
- Analyze product-wise transaction volumes
- Evaluate manager performance
- Generate actionable business insights through visualization
- Python
- Pandas
- NumPy
- Matplotlib
- Jupyter Notebook
Banking-Customer-Transaction-Analytics/
│
├── dataset
│ └── goldman_sachs.csv
│
├── notebook
│ └── Python_Project_Sujal_Agrahari.ipynb
│
├── screenshots
│ ├── 01_risk_score_distribution.png
│ ├── 02_credit_rating_distribution.png
│ ├── 03_monthly_credit_debit_trend.png
│ ├── 04_transaction_by_region.png
│ ├── 05_transaction_by_product.png
│ ├── 06_transaction_amount_distribution.png
│ ├── 07_account_type_distribution.png
│ ├── 08_credit_vs_debit_transactions.png
│ └── 09_top_managers.png
│
├── LICENSE
└── README.md
The dataset contains banking customer transaction records, including:
- Customer transactions
- Credit ratings
- Risk scores
- Account types
- Banking products
- Regional transaction details
- Credit & debit activity
- Manager assignments
Analyzed the distribution of customer risk scores to understand overall customer risk profiles.
Studied customer credit ratings to observe the spread of creditworthiness across customers.
Compared monthly credit and debit transaction amounts to identify financial activity trends over time.
Analyzed transaction volumes across different regions to identify high-performing markets.
Compared banking products based on total transaction volumes.
Visualized transaction amount distribution to understand customer spending behavior.
Examined the proportion of different customer account types.
Compared overall debit and credit transaction frequencies.
Identified managers handling the highest transaction volumes.
- Most customers fall within a moderate risk score range.
- Credit ratings are well distributed across customers.
- Debit transactions significantly outnumber credit transactions.
- Monthly transaction activity fluctuates throughout the observed period.
- Certain regions generate considerably higher transaction volumes.
- Home Loan and Credit Card products contribute the largest transaction amounts.
- Manager performance varies based on handled transaction volume.
- Customer account types are relatively balanced across the dataset.
👉 https://www.loom.com/share/85bb4222b14747b6a69eb60c780e9415
👉 https://www.loom.com/share/795ce8afef594cebb205bb7a99f2a8ab
- Python
- Pandas
- NumPy
- Data Cleaning
- Data Exploration
- Exploratory Data Analysis (EDA)
- Data Aggregation
- Statistical Analysis
- Data Visualization
- Financial Analytics
- Business Insights
- Problem Solving
Sujal Agrahari
Aspiring Data Analyst | Data Science & AI Enthusiast
This project was completed as part of the Internshala Data Science Training Program to strengthen practical Python and data analytics skills through a real-world financial transaction analysis case study.
⭐ If you found this project interesting, consider giving it a Star!