• Version
• Download 11
• File Size 664.73 KB
• File Count 1
• Create Date 11 May 2025
• Last Updated 11 May 2025

Banking Operations Through Data Analysis

Banking Operations Through Data Analysis

Authors:

Likhith Damodhar

Department of Computer Science Jain (Deemed-To-Be) University

Bangalore, India likhith.cr7fc@gmail.com

MD Shadab

Department of Computer Science Jain (Deemed-To-Be) University

Bangalore, India 21btrcs182@jainuniversity.ac.in

Preetham M

Department of Computer Science Jain (Deemed-To-Be) University

Bangalore, India preetham2301@gmail.com

Saraswat Akshay Anand

Department of Computer Science Jain

(Deemed-To-Be) University Bangalore, India akshayanand206@gmail.com

Abstract— In the era of digital transformation, the banking industry generates an enormous volume of transactional data every second. Analyzing this data can offer critical insights into customer behavior, operational efficiency, and fraud detection. This study explores a synthetic banking dataset with realistic operations using exploratory data analysis (EDA) techniques. By cleaning, preprocessing, and visualizing data using Python libraries like pandas, matplotlib, and seaborn, we identify key transaction patterns, customer preferences, and temporal usage trends. The study highlights the growing significance of data analytics in banking and proposes a modular system for ingesting, processing, and interpreting financial transaction data. Results showcase patterns such as high weekday activity, peak business hours, and the dominance of digital channels, providing a foundation for operational optimization and strategic decision-making.

Keywords— EDA, pandas, matplotlib, seaborn.