Food_Waste_Prediction_Project_Presentation.pptx

food waste prediction in restaurants

1. Food Waste Prediction in Restaurants Forecast which ingredients will go unsold to reduce waste & cost Presented by: [Your Name / Team]

2. Introduction Food waste is a major challenge in the restaurant industry. It leads to financial losses and environmental harm. This project develops a machine learning model to predict food wastage. Helps restaurants optimize inventory and reduce costs.

3. Problem Statement Restaurants often order or prepare more food than needed. This leads to ingredient wastage and increased expenses. No accurate prediction mechanism is in place. Need for a smart system to forecast wastage before it happens.

4. Objectives Predict ingredient wastage in restaurants. Help reduce operational costs and food waste. Assist in menu planning and inventory management. Promote sustainability in food services.

5. Dataset Description Historical restaurant data used: • Day of week, Weather, Special Events • Ingredient ordered & used • Wastage (kg), Dish sales count Dataset prepared with 200+ records.

6. Methodology Data Preprocessing: cleaning and encoding categorical features. Model Building: Random Forest Regressor chosen for predictions. Train-Test Split: 80% training, 20% testing. Evaluation using MAE (Mean Absolute Error) and R² Score.

7. Results Model Evaluation: • Mean Absolute Error (MAE): ~0.59 kg • R² Score: ~90.6% The model can accurately predict food wastage. Helps restaurants take preventive actions.

8. Future Scope Integrate real-time sales and weather data. Develop a mobile or web app for restaurant managers. Expand dataset with multiple restaurants and cuisines. Add cost-saving estimation and recommendations. AI-powered menu optimization for zero waste kitchens.

9. Conclusion The project demonstrates how AI/ML can solve real-world challenges. Food wastage can be predicted with high accuracy. Restaurants can save money and reduce environmental impact. Supports sustainable development goals (SDG 12: Responsible Consumption).