Authors:
H. Rakesh, R. Harshad, K. Sanjay Kumar, R. Regin, A. Anithalakshmi, G. Padmapriya

Addresses:
Department of Computer Science and Engineering, SRM Institute of Science and Technology, Ramapuram, Chennai, Tamil Nadu, India. Department of Science and Humanity, Dhaanish Ahmed College of Engineering, Chennai, Tamil Nadu, India. Department of Chemistry, Bharath Institute of Higher Education and Research, Chennai, Tamil Nadu, India.  

Abstract:

Food wastage is a major concern in the food industry, affecting economic and environmental sustainability. This project introduces a predictive analysis model to reduce food waste in restaurant inventory and menu planning. The system uses machine learning techniques to forecast food wastage based on factors like food type, guest count, quantity, event type, storage conditions, purchase history, preparation methods, seasonality, location, and pricing. A dataset containing food wastage patterns is preprocessed to manage missing values and categorical variables. Label encoding is applied to categorical features, while numerical features are standardized. The data is split into training and testing sets, and a Random Forest Regressor is trained for accurate predictions. The model achieved 92.79% accuracy, with a Mean Absolute Error (MAE) of 1.63 and an R² score of 0.9279, proving its reliability. A Tkinter-based GUI lets restaurant managers input parameters and receive real-time wastage predictions. The system categorizes wastage as minimal, moderate, or high and suggests inventory control measures. Future improvements include integrating Long Short-Term Memory(LSTM) for time-series forecasting, IoT sensors for real-time storage monitoring, and blockchain for supply chain transparency. By minimizing food wastage at the inventory stage, this project helps businesses optimize resources while promoting sustainability. 

Keywords: Predictive Analysis; Machine Learning; Random Forest Regressor; Mean Absolute Error (MAE); R² Score; Long Short-Term Memory (LSTM); IoT Sensors; Inventory Management.

Received on: 22/05/2024, Revised on: 19/07/2024, Accepted on: 30/09/2024, Published on: 14/12/2024

DOI: 10.69888/FTSIN.2024.000289

FMDB Transactions on Sustainable Intelligent Networks, 2024 Vol. 1 No. 4, Pages: 201-219

• Views : 26
• Downloads : 8

Download PDF