MUMBAI, India, Sept. 14 -- Intellectual Property India has published a patent application (202641107111 A) filed by Chokkamreddy Prakash; Mr. D. Srinivasu; Mrs. Bodhanapu Soujanya; Mrs. Bariniki Ratnamala; and Mr. Akurathi Lakshmi Pathi Rao on September 06, 2026, for Improving Mutual Fund Performance Analysis Through The Fusion Of Cnn-Lstm And Explainable Ai Techniques.
Inventors include Chokkamreddy Prakash; Mr. D. Srinivasu; Mrs. Bodhanapu Soujanya; Mrs. Bariniki Ratnamala; and Mr. Akurathi Lakshmi Pathi Rao.
The application for the patent was published on September 11, 2026, under issue no. 37/2026.
Abstract: Abstract The present invention relates to a system and method for improving mutual fund performance analysis using a hybrid deep learning framework integrated with explainable artificial intelligence techniques. The invention employs a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to capture both spatial and temporal patterns present in financial time-series data, including historical Net Asset Value (NAV), market indices, and macroeconomic indicators. The CNN component is configured to extract complex feature representations from multidimensional financial data, while the LSTM component models sequential dependencies and long-term trends to generate accurate performance predictions. The system further incorporates Explainable Artificial Intelligence (XAI) mechanisms, including feature attribution and local interpretability methods, to provide transparent and understandable explanations for the generated predictions. The proposed invention enhances prediction accuracy, reliability, and interpretability compared to conventional financial analysis methods. It enables investors, financial analysts, and asset management institutions to make informed decisions by providing predictive insights along with clear explanations of influencing factors. The system is scalable and adaptable to various financial domains, including mutual funds, stock markets, and portfolio management applications.
Disclaimer: Curated by HT Syndication.
