MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122166 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'ai-based stock recommendation system using adaptive proximal policy optimization.'
Inventor(s) include Dr. Saravanaguru Ra K; and Mr. Ruparelia Varun Sanjay.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides an AI-based stock recommendation system using adaptive Proximal Policy Optimization. The system includes a data collection module configured to fetch live stock market data from a financial data source and news articles from a news service, a sentiment analysis module configured to calculate sentiment scores from the news articles, a feature engineering module configured to calculate technical indicators from the live stock market data, an adaptive Proximal Policy Optimization model trainer configured to train a reinforcement learning model using clipped objective functions and adaptive learning rates, and a recommendation engine configured to generate stock recommendations based on the trained reinforcement learning model, the sentiment scores, and price change calculations."
Disclaimer: Curated by HT Syndication.
