• HARSHITA CHERUKURI
• SHREYAS MAHIMKAR
• SHALU JAIN
• DR SARITA GUPTA
• DR RAKESH GOEL

Predictive data-analytics has revolutionized field of Creditworthiness evaluation, Providing unparalleled precision and effectiveness in evaluating likelihood of credit defaults. This paper focuses on the innovative application of ML models to predict credit-default risk, harnessing rich, multifaceted data embedded within customer transactions. Established techniques for assessing credit risk commonly relied on static data points and subjective analysis, which could result in suboptimal decision-making and increased financial exposure. In contrast, ML models can process big amounts of dynamic transaction data , uncovering intricate patterns and correlations that are imperceptible to conventional approaches. Our study explores various ML techniques, covering decision trees, logistic regression, neural networks and random forests to determine their efficacy in predicting credit risk. By leveraging these models, Banks and financial firms can acquire comprehensive knowledge of client behavior, spot potential debtors with greater precision, and implement proactive measures to mitigate risk. The analysis points out the crucial role of data preprocessing, feature selection, and model evaluation. ensuring the robustness and reliability of the predictive models. Furthermore, the paper addresses the challenges inherent in using transactional data, such as data privacy concerns, the need for continuous model updating, and the integration of external factors that may influence credit risk. Through comprehensive analysis and comparative studies, we demonstrate that ML models not only enhance predictive accuracy but also provide scalable and adaptive solutions for credit risk management.

Predictive data analytics, Credit risk evaluation, ML models, Credit default risk, Customer transactions, Customer behaviour, Risk mitigation, Data preprocessing, Feature selection, Predictive accuracy

"Predictive Data Analytics In Credit Risk Evaluation: Exploring ML Models To Predict Credit Default Risk Using Customer Transaction Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 2, page no.335-346, February-2018, Available :http://www.jetir.org/papers/JETIR1802349.pdf

"Predictive Data Analytics In Credit Risk Evaluation: Exploring ML Models To Predict Credit Default Risk Using Customer Transaction Data", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 2, page no. pp335-346, February-2018, Available at : http://www.jetir.org/papers/JETIR1802349.pdf