Forecasting and Modelling of Food Demand Supply Chain using Machine Learning

Authors: Dr. M. A. Chaudhari, Aditi Phapale, Pranav Gagare, Tejas Kardile, Amruta Phatangare

Country: India

Full-text Research PDF File:   View   |   Download

Abstract: This paper presents a comprehensive software solution for addressing the challenges associated with predicting and managing the demand and supply of food in a dynamic environment. The system leverages machine learning algorithms, including XGBoost, LightGBM, and SARIMA, to provide accu- rate demand forecasting and optimize inventory and distribution by modelling supply chains. The user-friendly interface allows administrators to interpret machine learning model outputs and make informed decisions, while the historical data module provides essential access to past trends and patterns for training and validating machine learning models. The paper discusses the system’s key features, such as demand forecasting, inventory management, data analytics dashboard, and fulfillment center allocation, and outlines the nonfunctional requirements, including performance, safety, security, and software quality attributes. The proposed solution aims to provide valuable insights for stakeholders in the food industry, ultimately contributing to more efficient and informed decision- making in the management of food demand and supply chains.

Keywords:

Paper Id: 232389

Published On: 2025-04-18

Published In: Volume 13, Issue 2, March-April 2025

Share this