Loan Sanctioning Prediction System
Aditi Kacheria1, Nidhi Shivakumar2, Shreya Sawkar3, Archana Gupta4
1Aditi Kacheria, Student, Department of Computer Engineering, K. J. Somaiya College of Engineering, Mumbai, India.
2Nidhi Shivakumar, Student, Department of Computer Engineering, K. J. Somaiya College of Engineering, Mumbai, India.
3Shreya Sawkar, Student, Department of Computer Engineering, K. J. Somaiya College of Engineering, Mumbai, India.
4Prof. Archana Gupta, Assistant Professor, Department of Computer Engineering, K. J. Somaiya College of Engineering, Mumbai, India.
Manuscript received on August 05, 2016. | Revised Manuscript received on August 06, 2016. | Manuscript published on September 05, 2016. | PP: 50-53 | Volume-6 Issue-4, September 2016. | Retrieval Number: D2904096416/2016©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: People operating in banks face lots of issues which involve approval of a loan. In the 21st century, people often rely on technology to tackle such issues. This paper proposes a loan sanctioning system which determines whether or not a loan should be given to a person, based on certain attributes. In spite of banks following stringent rules and regulations and conducting meticulous background checks while sanctioning a loan and keeping in mind the probability of the person’s ability to return the loan, often such situations are faced where in, the person is unable to repay the loan that has been given to him. In this paper, the system that we propose for the bankers will help them predict the credible customers who have applied for loan, thereby improving the chances of their loans being repaid in time. This classification is done using Naïve Bayesian algorithm. In order to improve the classification accuracy, the quality of the data is improved before classifying it by using K-NN and Binning algorithms. This system uses these algorithms in order to yield a better efficiency so as to reduce the possibility of such a problem. The proposed system additionally facilitates self-confirmation regarding the same for the commoner.
Keywords: Binning, Data mining, K-NN, Naïve Bayesian