Download PDFOpen PDF in browser

Develop a Flask-Based Web App Using the Logistic Regression Algorithm to Detect Credit Card Fraud in Machine Learning

EasyChair Preprint no. 11745

6 pagesDate: January 12, 2024


The Credit Card Fraud Detection (CCFD) project represents a proactive approach to enhancing financial security by leveraging machine learning techniques in the development of a Flask-based web application. As digital transactions become increasingly prevalent, the need for robust fraud detection mechanisms becomes paramount. This project aims to address this challenge by employing advanced analytical methods and historical transaction data to predict and prevent potential fraudulent activities in real-time. At its core, the CCFD project focuses on model training, a foundational step that enables the system to scrutinise transaction patterns comprehensively. By learning from extensive datasets and historical fraud cases, the model becomes proficient in identifying suspicious activities, thereby improving the accuracy of fraud detection. This training process is pivotal, as it equips the system to adapt to evolving fraud tactics and stay ahead of malicious actors. The development of the Flask-based web application acts as the gateway between advanced machine learning and seamless user interaction. The application offers an intuitive user interface, allowing users to effortlessly input their transaction details. This interface serves as a portal through which users can access the benefits of machine learning-powered fraud detection without requiring specialised technical knowledge.

Keyphrases: data analysis, fraud detection, security measures

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {A Vaidhegi and H Aswini},
  title = {Develop a Flask-Based Web App Using the Logistic Regression Algorithm to Detect Credit Card Fraud in Machine Learning},
  howpublished = {EasyChair Preprint no. 11745},

  year = {EasyChair, 2024}}
Download PDFOpen PDF in browser