Analysis of Loan Availability using Machine Learning Techniques

Abstract

In the banking system, banks have a variety of products to provide, but credit lines are their primary source of revenue. As a result, they will profit from the interest earned on the loans they make. Loans, or whether customers repay or default on their loans, affect a bank's profit or loss. The bank's Non-Performing Assets will be reduced by forecasting loan defaulters. As a result, further investigation into this occurrence is essential. Because precise forecasts are essential for benefit maximisation, it's crucial to analyse and compare the various methodologies. The logistic regression model is an important predictive analytics tool for detecting loan defaulters. In order to assess and forecast, data from Kaggle is acquired. Logistic Regression models were used to calculate the various performance indicators. The models are compared using performance metrics like sensitivity and specificity. In addition to checking account details (which indicate a customer's wealth), the model is significantly better because it includes variables (customer personal attributes such as age, objective, credit score, credit amount, credit period, and so on) that should be considered when correctly calculating the probability of loan default. As a result, using a logistic regression approach, the appropriate clients to target for loan issuance can be easily identified by evaluating their plausibility of loan default. The model implies that a bank should assess a creditor's other attributes, which play a critical role in credit decisions and forecasting loan defaulters, in addition to giving loans to wealthy borrowers.

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 — 27 citations exist upstream.

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