Reducing food waste in the HORECA sector using AI-based waste-tracking devices.

Area of Science:

• Environmental Science
• Computer Science
• Food Science

Background:

• Food waste is a significant environmental and economic issue in the HORECA sector.
• Existing methods for tracking food waste are often manual and labor-intensive.
• Overproduction and consumer leftovers are major contributors to avoidable food waste.

Purpose of the Study:

• To assess the effectiveness of an AI-based, automatic waste-tracking system for food waste reduction.
• To evaluate the system's impact on staff awareness and corrective action implementation.
• To determine the transferability and sustainability of the intervention across different HORECA settings.

Main Methods:

• Implementation of AI-powered waste-tracking devices utilizing computer vision and deep learning.
• Real-time weighing and optical segregation of food waste in restaurants, hotels, and catering services.
• Baseline data collection and post-intervention analysis of food waste quantities and cost.

Main Results:

• Food waste reduction ranged from 23% to 51% in most establishments, with a notable increase in one Swiss hotel.
• The system successfully raised staff awareness, leading to targeted corrective actions.
• Wasted food costs per meal decreased by up to 39% compared to baseline.
• Vegetables and prepared foods were identified as primary waste contributors.

Conclusions:

• AI-based automatic waste-tracking systems are effective tools for reducing food waste in the HORECA industry.
• The intervention demonstrates transferability and long-term sustainability across various hospitality settings.
• Data-driven insights from the system facilitate significant reductions in food preparation and overproduction waste.
• Further research should integrate consumer-level interventions with waste-tracking technology for enhanced impact.