Machine Learning based Loan Allocation Prediction System for Banking Sector
- Resource Type
- Conference
- Authors
- Sinha, Jaya; Astya, Rani; Tripathi, Komal; Verma, Aparna; Verma, Mansi
- Source
- 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N) Advances in Computing, Communication Control and Networking (ICAC3N), 2021 3rd International Conference on. :1614-1619 Dec, 2021
- Subject
- Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Engineering Profession
Fields, Waves and Electromagnetics
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Computational modeling
Organizations
Machine learning
Banking
Forestry
Predictive models
Resource management
Random forest classifier
feature extraction
heatmap
confusion matrix
predictive analysis
- Language
Banking sector in India is overwhelmed with numerous applications by individual customers or organizations for different types of loans. Every year, we hear about a variety of cases in which customers fail to repay the major part of their loans to banks, causing them to incur significant losses. Precise evaluation of credit risk for customers is one of the major factors on which success or failure of any organization depends. Credit risk evaluation helps banking organizations to classify borrowers as defaulter or not before allocating the credit loan. This still remains a challenging task for banks in current scenario and this task is accomplished by analyzing the recorded past history of loan availing customer. In this paper, we have proposed a bank loan defaulter prediction model based on various machine learning techniques. The study focus on analyzing these stored records or experiences for better prediction by applying different machine learning techniques and identifying the most suitable one. The main goal of this model is to determine whether authorizing a loan for a specific customer is risky or not as loan amount should be repaid within given timeframe.