MUMBAI, India, March 13 -- Intellectual Property India has published a patent application (202621011112 A) filed by Symbiosis International, Pune, Maharashtra, on Feb. 2, for 'system and method for retail demand forecasting using gradient boosting with bayesian hyperparameter optimization.'
Inventor(s) include Dr. Shreyas Rajendra Hole.
The application for the patent was published on March 13, under issue no. 11/2026.
According to the abstract released by the Intellectual Property India: "The present invention discloses a retail demand forecasting system (100) integrating Light Gradient Boosting Machine with Bayesian hyperparameter optimization. The system comprises a Data Acquisition Module (110) for collecting transactional data including temporal and promotional features, a Data Preprocessing Module (120) for data cleansing and feature engineering including rolling window calculations, a LightGBM Model Engine (130) implementing histogram-based learning and leaf-wise tree growth, a Bayesian Hyperparameter Optimization Module (140) employing Tree-structured Parzen Estimators (142) for automated parameter tuning across learning rate, number of leaves, depth, and regularization parameters, and a Prediction Output Module (150) for generating forecasts with feature importance analysis. The system achieves R-squared of 0.94 and MAPE of 5.7 percent with 35 percent reduction in tuning time compared to grid search methods. The invention provides scalable, interpretable forecasting for beverage retail inventory optimization."
Disclaimer: Curated by HT Syndication.
