This project provides an in-depth analysis of a real banking transaction dataset to uncover valuable insights into customer behavior, peak transaction times, and product sales performance. The analysis leverages Python’s data science ecosystem to transform raw data into actionable insights.
The primary goals of this analysis are to answer the following questions:
- Q1: Is there a specific pattern in customer purchase timing (day of the week, time of day)?
- Q2: Which stores have the most sales?
- Q3: What are the best-selling products?
- Checking for missing values (
NaN) - Convert Jalali dates to Gregorian using
jdatetime - Create new time-based features (day_of_week, hour)
- Identify peak hours and days for transactions
- Analyze total sales by store and product
- Generate visualizations for better interpretation
- Detect seasonal or weekly patterns
- Rank stores/products by performance
The following Python libraries are required to run the analysis:
pandas: For data manipulation and analysis.matplotlib: For data visualization.jdatetime: For converting Shamsi (Jalali) dates to Gregorian dates.
You can install these dependencies using pip:
pip install pandas matplotlib jdatetime git clone https://github.com/ZahraSahranavard/Bank-Transaction-Analysiscd Bank-Transaction-AnalysisBanking_transaction_data_analysis.ipynb- Integration with machine learning models for sales forecasting
- Development of an interactive dashboard (using Plotly/Dash or Streamlit)
- Additional insights such as customer segmentation and basket analysis
For further improvements to this project, I have planned some advancements. Follow this repository to stay updated on them.😃
This project is licensed under the MIT License - see the LICENSE file for details.
Developed by Zahra Sahranavard
For inquiries: zahra.sahranavard7622@iau.ir