Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{180511,
        author = {Aditya Gajjal and Prof. Supriya Manwar and Prof. Vrushali Wankhede and Abdul Kadir and Sahiloddin Shaikh and Aditya Naik},
        title = {Loan Eligibility Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {1},
        pages = {1967-1975},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=180511},
        abstract = {This In the current era of digital finance, the 
automation of loan approval processes has become 
increasingly crucial for both financial institutions and 
applicants. Traditional loan approval systems are 
time-intensive and often subject to human bias or 
error. This paper presents an intelligent, explainable, 
end-to-end loan eligibility prediction system that 
leverages modern machine learning techniques to 
assist in the decision-making process. The proposed 
architecture integrates data preprocessing, model 
training, and deployment via a RESTful API, coupled 
with an intuitive frontend interface for user 
interaction. 
By 
incorporating 
explainability 
mechanisms into the pipeline, the system not only 
provides prediction results but also helps applicants 
understand the rationale behind them, thereby 
increasing transparency and trust in automated 
financial assessments. The system is developed using 
Python and its data science ecosystem, including 
scikit-learn, pandas, and NumPy for model training 
and preprocessing. Flask is utilized to serve the 
trained model through an API, while a responsive 
frontend built with HTML5, CSS3, and JavaScript 
provides a seamless user experience. The model is 
optimized using cross-validation and hyperparameter 
tuning, achieving high accuracy and interpretability 
through 
feature 
analysis 
and SHAP-based 
visualizations. Evaluation results confirm that the 
system effectively predicts loan eligibility and explains 
contributing factors to the decision, demonstrating its 
practical 
applicability 
environments.},
        keywords = {Loan Eligibility Prediction, Machine  Learning, Data Preprocessing, Model Interpretability,  Flask API Deployment, SHAP Values, Automated  Financial Decision- Making},
        month = {June},
        }