Customer Loan Eligibility Prediction using Machine Learning Algorithms in Banking Sector

Abstract

As there is rapid growth in the banking and financial sector every individual is relying on the banks and the loans provided by global and national banking sectors. In general, bank will be providing loans based on the net property value and asserts of the bank to the limited people who are eligible, and approvals of the loans will be based on the income resources of the customers. In this project various machine learning techniques are implemented to predict the eligibility of the customer for a loan. Customer data is collected based on various banks and accessing the customer profiles to analyze the data based on the parameters which are essential to integrate with the machine learning techniques. Analyze the data and provide the results based on the customer profile to grant the loans using machine learning approach is most advanced than traditional loan approval-based systems. The key objectives of the project are data cleansing, key attributes selection and performance comparison of decision tree, random forest, support vector machine, K-nearest neighbor, and decision tree with AdaBoost machine learning methods on predicting the customer loan eligibility. Data is divided into training and testing parts and model is trained using train dataset and the model performance is evaluated on test dataset. Results evidence that ensemble model decision tree with adaboost technique given more accuracy compared to other implemented models.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 41 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.