FASTag transaction analysis using Python (Pandas, NumPy, Matplotlib) to explore toll revenue trends, traffic patterns, bank usage, and transaction failures.
FASTag Transaction Analysis (Python) Project Overview
This project analyzes FASTag toll transaction data using Python to generate business insights related to revenue trends, traffic patterns, bank-wise transactions, and transaction failures.
The analysis is performed using Python, Pandas, NumPy, and Matplotlib to simulate a real-world data analyst scenario in the banking and transportation domain.
The goal of this project is to demonstrate exploratory data analysis (EDA), data cleaning, and visualization skills using structured transaction data.
Business Problem
FASTag enables automatic toll payments across highways, generating large volumes of transaction data every day. Analyzing this data helps organizations:
Monitor toll revenue, Identify peak traffic hours, Detect failed or reversed transactions, Evaluate toll plaza performance, Detect abnormal or high-value transactions.
This project performs data analysis on FASTag transaction data to generate insights that support operational and financial decision-making.
Tools and Technologies: Python, Pandas, NumPy, Matplotlib, Jupyter Notebook / Google Colab
Analysis Performed : Data Exploration, Dataset shape and structure, Summary statistics, Missing value detection, Transaction Analysis, Total number of transactions, Transaction status distribution, Failed and reversed transaction analysis, Revenue Analysis, Total toll revenue, Revenue by toll plaza, Vehicle type revenue analysis, Daily revenue trends, Traffic Pattern Analysis, Hour-wise transaction volume, Identification of peak traffic hours, Bank Analysis, Bank-wise transaction count, Identification of most frequently used bank, Wallet Balance Validation, Checking wallet balance consistency, Detecting incorrect deductions, Anomaly Detection, Identifying unusually high-value transactions using statistical thresholds
Key Insights 1.Certain toll plazas generate significantly higher revenue. 2.Traffic peaks during typical commute hours. 3.A majority of transactions are successful, while a small percentage fail or are reversed. 4.Some banks process more FASTag transactions than others. 5.High-value transactions can be detected using statistical anomaly detection techniques.
How to Run the Project 1.Open the notebook in Jupyter Notebook or Google Colab. 2.Upload the dataset file. 3.Run all cells in the notebook. 4.The notebook will perform data analysis and generate visualizations.
Project Objective This project demonstrates data analysis skills using Python, including: 1.Data exploration 2.Data cleaning 3.Aggregation and grouping 4.Visualization 5.Business insight generation
It simulates how a Data Analyst would analyze transaction data in a banking or fintech environment.
Author
Data Analytics Portfolio Project
Skills demonstrated:
1.SQL 2.Python 3.Data Analysis 4.Power BI 5.Data Visualization