Intellectual Property India Publishes Patent Application for 'Machine Learning Based Stock Prediction In Indian Economy' Filed by Dr. Renuka Ganesh Karpe; Arun Jalindar Divate; Dr Megha Jain; Prof. Vilas Shankar Nichit; Dr. S. Saravanan; Ran Vijay Singh; Dr. F. Leena Vinmalar; and Dr. Manasi S. Kurtkoti

MUMBAI, India, May 29 -- Intellectual Property India has published a patent application (202621043228 A) filed by Dr. Renuka Ganesh Karpe; Arun Jalindar Divate; Dr Megha Jain; Prof. Vilas Shankar Nichit; Dr. S. Saravanan; Ran Vijay Singh; Dr. F. Leena Vinmalar; and Dr. Manasi S. Kurtkoti, Pune, Maharashtra, on April 4, for 'machine learning based stock prediction in indian economy.'

Inventor(s) include Dr. Renuka Ganesh Karpe; Arun Jalindar Divate; Dr Megha Jain; Prof. Vilas Shankar Nichit; Dr. S. Saravanan; Ran Vijay Singh; Dr. F. Leena Vinmalar; and Dr. Manasi S. Kurtkoti.

The application for the patent was published on May 29, under issue no. 22/2026.

According to the abstract released by the Intellectual Property India: "Stock market trading is a significant and prominent activity within the financial markets. Given the inherent unpredictability and volatility in stock prices, an investor continuously seeks methods to forecast future trends to mitigate losses and maximise profits. Nonetheless, it is undeniable that no strategy currently exists to predict future market patterns with absolute precision, while several ways are being investigated to enhance the predictive efficacy of models to the greatest extent feasible. Recent advancements in Machine Learning (ML) and Deep Learning (DL) have led to the deployment of numerous algorithms for stock price prediction. The findings indicated that Long Short-Term Memory, possessing time-independence attributes and superior predictive accuracy, emerged as the most effective machine learning technique for forecasting the fluctuations of the Indian stock markets. Furthermore, the predictive accuracy of all machine learning algorithms, with the exception of Long Short-Term Memory, fluctuates over time. Conversely, support vector machines and linear regression models, characterised by their minimal predictive accuracy and maximal mistakes, demonstrated the least suitability for forecasting the movements of Nifty and Sensex, respectively."

Disclaimer: Curated by HT Syndication.