• MD. Mobeen
• Ch. Dharani

In Automated credit analysis has evolved significantly with the advent of advanced machine learning techniques, enabling more accurate and efficient credit risk assessment. This study proposes an innovative approach that combines the strengths of recurrent neural networks (RNNs) and CatBoost classifiers to enhance credit scoring models. RNNs are adept at capturing temporal dependencies in sequential data, making them ideal for modeling the time-varying aspects of credit behavior. CatBoost, a gradient boosting algorithm specifically designed for handling categorical features, complements RNNs by efficiently processing the categorical variables prevalent in credit datasets. By integrating these two methodologies, our approach not only improves predictive accuracy but also enhances model interpretability, providing valuable insights into the factors influencing credit risk. Experimental results on benchmark credit datasets demonstrate the superiority of the combined RNN and CatBoost model over traditional credit scoring methods, highlighting its potential for deployment in financial institutions to facilitate more reliable and transparent credit decision-making processes.

Automated credit analysis, Recurrent Neural Networks, CatBoost classifier, credit risk assessment, machine learning, temporal modeling, categorical data handling, predictive analytics, hybrid models, financial technology.

"An Automated Credit Analysis Using Recurrent Catboost Classifier", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.392-397, June-2024, Available :http://www.jetir.org/papers/JETIRGL06066.pdf

"An Automated Credit Analysis Using Recurrent Catboost Classifier", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pp392-397, June-2024, Available at : http://www.jetir.org/papers/JETIRGL06066.pdf