Spatial-Temporal Event Analysis as a Prospective Approach for Signalling Emerging Food Fraud-Related Anomalies in...

Area of Science:

• Food science and technology
• Supply chain management
• Data science and artificial intelligence

Background:

• Food traceability systems rely on unique product and batch identification along the supply chain.
• Spatial-temporal patterns of these codes can offer insights into emerging food fraud.
• Current food fraud detection methods could be advanced by analyzing these patterns.

Purpose of the Study:

• To explore the potential of analyzing spatial-temporal patterns of scanned food codes for food fraud detection.
• To project the transfer and implementation of artificial intelligence approaches from other fields to food supply chains.
• To develop future applications for early warning systems for emerging food frauds.

Main Methods:

• Utilizing user-scanned codes on food packaging to generate spatial-temporal datasets.
• Applying artificial intelligence (AI) techniques to analyze these datasets.
• Examining parallel approaches developed in biology, medicine, and credit card fraud detection for potential transfer.

Main Results:

• Spatial-temporal patterns of scanned codes have not been previously studied in the context of food fraud.
• AI analysis of these patterns can reveal anomalies indicative of supply chain fraud.
• Successful implementation of similar pattern analysis exists in other domains.

Conclusions:

• The analysis of spatial-temporal patterns of scanned food codes presents a novel avenue for detecting food fraud.
• Artificial intelligence offers powerful tools for identifying anomalies in food supply chains.
• This research lays the groundwork for developing proactive, AI-driven early warning systems against food fraud.