Exploring the impact of artificial intelligence of financial technology: a used-case of credit card fraud detection
The detection of credit card fraud remains a critical challenge in the digital age, prompting extensive research into effective methodologies and techniques. This study contributes to the field by employing logistic regression and analyzing a dataset comprising 1,754,155 transactions from Axis Bank...
| Main Author: | |
|---|---|
| Format: | Final Year Project / Dissertation / Thesis |
| Published: |
2024
|
| Subjects: | |
| Online Access: | http://eprints.utar.edu.my/6713/ http://eprints.utar.edu.my/6713/1/202310%2D41_GanJiaSheng_2102078_FinalisedThesis_GAN_JIA_SHENG.pdf |
| Summary: | The detection of credit card fraud remains a critical challenge in the digital age, prompting extensive research into effective methodologies and techniques. This study
contributes to the field by employing logistic regression and analyzing a dataset comprising 1,754,155 transactions from Axis Bank in India. Through Pearson and Spearman correlations, it identifies Transaction Amount as a significant predictor of fraud, underscoring its pivotal role in fraud detection. Furthermore, the study explores
the implications of threshold setting in machine learning models for fraud detection, emphasizing the balance between false positives and false negatives. It also highlights
the importance of diverse datasets and the adoption of multiple analysis methods to enhance the accuracy and reliability of fraud detection systems. The findings provide
valuable insights for regulators, financial institutions, and researchers, aiding in the development of evidence-based policies and the refinement of fraud detection models
to combat evolving fraud threats effectively.
|
|---|