Predictive Analysis in Banking using Machine Learning

Gupta Ashwin Arunkumar, Chaurasiya Ravi Panchuram, Khambati Mohammed Aadil Afzal, Niraj Sureshchand Yadav and Uma Goradiya

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2023, vol. 9, issue 2, 434-439

Abstract: This paper discusses the utilization of machine learning for predicting loan approval and credit card fraud detection. Specifically, the paper proposes the use of the Random Forest Algorithm and Support Vector Machine Learning Algorithm for achieving better accuracy. The banking sector's main objective is to ensure their assets are in safe hands, and to achieve this, a verification process is carried out. However, the process takes a long time, and there is no guarantee of selecting deserving applicants. To address this problem, a system has been developed that predicts the suitability of an applicant for loan approval based on a model trained using machine learning algorithms. The system has achieved 92% accuracy using the Random Forest Algorithm. The system has a user interface web application where users can input necessary details for the model to predict. The system's drawback is that it considers multiple attributes, whereas, in real life, a loan application may be approved based on a single strong attribute, which the system cannot detect. With the increasing number of online transactions, credit card usage has become more prevalent. Losing physical credit cards or credit card information can result in significant financial loss. Therefore, there is a need to detect fraudulent transactions and secure them. To address this issue, the paper proposes the use of the Support Vector Machine Algorithm, which focuses on analyzing and preprocessing data sets and deploying fraud detection using Credit Card Transaction data.

Keywords: Machine Learning (ML); Random Forest; Loan Approval; Support Vector Machine Algorithm; Credit Card Fraud (search for similar items in EconPapers)
Date: 2023
Note: Article URL: https://ijsrcseit.com/CSEIT2390247
References: Add references at CitEc
Citations:

Downloads: (external link)
https://ijsrcseit.com/CSEIT2390247 Article URL (text/html)
https://ijsrcseit.com/paper/CSEIT2390247.pdf Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:jbh:ijsrcs:v9:y2023:i2:id:hcseit2390247

DOI: 10.32628/CSEIT2390247

Access Statistics for this article

More articles in International Journal of Scientific Research in Computer Science, Engineering and Information Technology from International Journal of Scientific Research in Computer Science, Engineering and Information Technology
Bibliographic data for series maintained by Pankaj Sharma (USA) ().