MUMBAI, India, July 11 -- Intellectual Property India has published a patent application (202541052732 A) filed by Muthoot Pappachan Technologies, Trivandrum, Kerala, on May 30, for 'a system and method for explainable credit risk analysis and real-time loan approval.'
Inventor(s) include Mr. Jayakrishnan P; and Dr. John Paul Martin.
The application for the patent was published on July 11, under issue no. 28/2025.
According to the abstract released by the Intellectual Property India: "The present invention generally relates to a system for explainable credit risk analysis and real-time loan approval using deep learning models. The system integrates structured and unstructured credit-related data from various sources, including transactional, demographic, socio-economic data, collateral images, and voice recordings. A data pre-processing module cleans and transforms the data, while a consolidation module merges and scales features. Deep learning models extract additional attributes from images and speech-classifying collateral characteristics and analyzing customer sentiment. These enriched attributes are fed into classification and regression models to assess creditworthiness and predict eligible loan amounts. A loan value calculation module determines the final loan amount based on predicted percentage and collateral value. To enhance trust, an explainability module provides clear justifications for model decisions by identifying key contributing factors. The complete system is integrated into a loan origination platform to enable real-time, transparent credit risk assessment and loan approval."
Disclaimer: Curated by HT Syndication.
