top of page

Promise & perils of predictive analytics for food safety

Food safety incidents, like product recalls, border rejections and fraud incidents, unfortunately occur every day around the world. They are a very common, yet challenging, case that food safety experts have to deal with. What if there was a way for food companies to be notified about emerging risks that really need their attention and action? They could be prepared before a recall happens rather than receiving a notification that a recall has happened, or a consumer has complained. We are talking about something like a digital crystal ball, which the food safety professionals would ask every morning to find out what is going to happen, before it does.

Predictive analytics can be that digital crystal ball. This state-of-the-art technology offers invaluable information for food safety purposes. It is not magic, nor is it yet widely adopted by food safety professionals. However, we see it out there in action among the pioneers showing the way.

Agroknow harnesses the power of cutting-edge Hyper Performance Computing (HPC) solutions developed by the Cybele project, in order to generate reliable risk predictions for major international food manufacturers. We combine artificial intelligence, advanced data analysis and scientific expertise to provide trustworthy food safety predictions for the entire supply chain. Thus, we enable food companies to prevent product recalls and other food safety incidents, maintain their brand’s reputation and avoid financial damages. Food safety and quality assurance teams can use this intelligence to build a robust proactive strategy and mitigate emerging risks in their global supply chain.

But we are not the only ones. There are many others, like the ones we heard talking at the GFSI21 Special Session on the Promise & Perils of Predictive Analytics for Food Safety, funded by Cybele, about how they use AI to take mission critical decisions:

Amazon, who is deploying natural language processing and predictive modeling to process safety data about the billions of items in its marketplace.

Coca-Cola, who is using a food risk prediction platform to monitor and prevent external risks across its global supply chain.

The U.S. FDA, who is using a machine learning system that processes data from screening import shipments, decides which shipments to examine, and indicates which food in the shipment to sample for laboratory testing.

But let us also keep in mind the chasm between these daring innovators and the silent majority. We need to find ways to cross this chasm by building a bridge of food safety best practices. We believe that this is an opportunity for reflection; an opportunity to better understand the solutions that this technology can bring to food safety.



bottom of page