Fraud Detection in Banking Transactions Using Machine Learning and Streamlit-Based Deployment

DOI

10.2991/978-94-6239-693-7_98How to use a DOI?

Keywords

Fraud Detection; Machine Learning; Banking Transactions; Streamlit; Data Preprocessing; Real-Time Monitoring; Visualization

Abstract

The paper provides a deployable banking transaction fraud detection system, written in Python and Streamlit, which uses a pre-trained supervised machine learning classifier as an interactive web-based dashboard. Structured transactional data is also processed in the system in seven engineered features groups: Transaction Details, Cardholder Information, Device and Network Information, Historical Data, Behavioral Data, Security Features, and External Data. At runtime a serialized classification model is loaded and used on processed inputs with categorical labelling and feature scaled with a stored scaler with the aim of preserving inference consistency. The probabilistic output of the model is extracted and synthesized together to arrive at scores representing probability of fraud, the score is converted to binary counts of prediction according to a decision logic using a threshold. The application enables the batch analysis of transactions through CSV upload, real-time and manual entry of transaction the simulation of constant flow of transactions to be operated under the continuous monitoring. Interactive visualizations of probability distribution of frauds, statistics of their rate, and their trend over time made in Plotly are displayed. It is contrary to the completely theoretical studies of fraud detection, as the study deals with practical implementation of combining the stages of preprocessing, prediction, alerting and visualization within the same interface. The system provides an idea of how machine learning inference dashboards would be projected into effective prototype of a fraud monitoring function that could be implemented as a working financial analytics atmosphere.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - N. Naveen Kumar
AU  - J. Nandhitha
AU  - R. Anandha Sree
AU  - B. Gracelin Sheena
PY  - 2026
DA  - 2026/06/16
TI  - Fraud Detection in Banking Transactions Using Machine Learning and Streamlit-Based Deployment
BT  - Proceedings of the International Conference on Intelligent Systems for a Sustainable Future (ISSF 2026)
PB  - Atlantis Press
SP  - 1015
EP  - 1026
SN  - 2589-4919
UR  - https://doi.org/10.2991/978-94-6239-693-7_98
DO  - 10.2991/978-94-6239-693-7_98
ID  - Kumar2026
ER  -