An Efficient Loan Approval Status Prediction Using Machine Learning

Abstract

Banks derive a substantial portion of their profits from loans, making the loan approval process a vital undertaking for these financial institutions. However, it is becoming increasingly challenging to accurately assess loan requests and manage the risks associated with loan defaults. Due to this, scientists have been studying methods for forecasting loan approval systems, and machine learning techniques have proven to be effective in handling large amounts of data. In this study, we utilize algorithms such as K-Nearest Neighbours and Decision Trees to predict loan approval for customers. We also introduce a novel algorithm, the Support Vector Classifier, which demonstrates superior accuracy and is used to deploy the model. With these machine learning techniques, we are able to develop a bank loan prediction system that automatically selects eligible candidates for loan approval. The research study explored the application of machine learning algorithms in predicting the status of loans. SVM was one of the algorithms evaluated, and it achieved an accuracy score of 83%. Nonetheless, the research also revealed that various factors can impact the efficacy of SVM, such as the quality of the data, the choice of hyperparameters and the existence of data bases in the data or model. Overall, the study found that SVM has the potential to be a valuable tool for loan status prediction, but its success will depend on a number of factors.

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 — 21 citations exist upstream.

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