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{183232,
        author = {Vignesh SR and Rajeshwaran K and Valentina R and Trishanthan R},
        title = {FOOD DEMAND FORECASTING ANALYSIS},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {498-508},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183232},
        abstract = {This project aims to forecast food demand for various outlets or regions using historical sales data and external factors like seasonality, promotions, and weather. Accurate forecasting helps reduce food waste and optimize supply chains. The dataset includes sales records, external variables, and time-series information. Exploratory Data Analysis (EDA) identifies seasonal trends, the impact of promotions, and regional demand patterns. Multiple machines learning models, including Linear Regression, Random Forest, Gradient Boosting, and ARIMA, SARIMA are used for predictions. Model performance is evaluated using metrics like MAE, RMSE, and R² Score. The best-performing model's forecasts are visualized using Tableau to support decision-making. The results indicate that Random Forest Regression is the best-performing model, demonstrating strong predictive accuracy with the lowest errors. Decision Tree Regression also showed moderate performance, followed by Gradient Boosting Regression and k-Nearest Neighbors Regression, which exhibited higher errors and lower accuracy. Based on this evaluation, Random Forest Regression is recommended for reliable food demand forecasting.},
        keywords = {Deep learning, Machine learning, Time series analysis and demand analysis},
        month = {August},
        }