Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174572,
        author = {K.Hari veerraju and S.Ravi Kiran and G.Kusuma Kumari and K.Sai Kishore and J.Likhit},
        title = {BIGMART SALES PREDICTION USING LIGHTGBM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {35-39},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174572},
        abstract = {Sales forecasting maintains an important position in retail because it aids businesses with inventory management and cost reduction to create strategic decisions. The research uses Light Gradient Boosting Machine (LightGBM) to forecast BigMart sales by analyzing historical data combined with product attributes and store-related information. The predictive model benefits from various feature engineering techniques which include One-Hot Encoding and Ordinal Encoding and Polynomial Features. The model performance reaches its peak through systematic adjustments of its hyperparameters. The experimental evaluation assesses LightGBM by examining its performance against Linear Regression as well as Decision Trees Random Forests and XGBoost through R² and Mean Squared Error (MSE) and Mean Absolute Error (MAE). LightGBM demonstrates superior performance compared to traditional models in terms of accuracy together with operational speed thereby capturing sophisticated sales relationship patterns. The application of LightGBM generates data-driven findings that enable BigMart to make enhanced pricing decisions, better control inventory flow, and boost operational operations. LightGBM shows strong capabilities for processing extensive retail data according to the research findings which establishes its value for forecasting sales in evolving market conditions. The research uses LightGBM to predict sales while employing Machine Learning approaches and performing Feature Engineering tasks alongside Hyperparameter Tuning techniques with Predictive Analytics methods.},
        keywords = {Sales Forecasting, LightGBM, Machine Learning, Feature Engineering, Hyperparameter Tuning, Predictive Analytics},
        month = {March},
        }