The Qassim University and Saudi Food and Security Authority hackathon attracted more than 220 innovative ideas to employ data and artificial intelligence in reducing food loss and waste.
Conclusion of Qassim University hackathon with 50 projects qualifying out of 220 ideas
Scientific distinction between food loss and waste and potential machine learning applications
Limits of innovative project maturity and stages of transition to actual production
Upcoming milestones to turn qualified ideas into field trials
Frequently asked questions
Conclusion of Qassim University hackathon with 50 projects qualifying out of 220 ideas
Qassim University concluded a two-day innovation hackathon organized by the university through the Institute of Studies and Consulting Services in cooperation with the Saudi Food and Security Authority in the Kingdom of Saudi Arabia. According to a report published by the Saudi Press Agency (SPA) from Buraidah on October 25, 2026, the challenge received more than 220 proposed ideas, and a total of 50 entries qualified for the closing ceremony, divided evenly between 25 in-person entries and 25 remote entries. These figures describe the submitted proposals and finalists, and do not represent operational artificial intelligence systems actually deployed in Saudi food supply chains.
The innovative competition addressed both food loss and waste issues across five key stages of the food value chain, explicitly encouraging the use of technology, data, and artificial intelligence to improve supply chain planning and measure metrics for wasted or lost food. This initiative aligns with the National Program to Reduce Food Loss and Waste (“Lidoom”) and the broader priorities of Saudi Vision 2030, while the official statement did not specify how many of the 220 proposals actually used machine learning, nor did it include independently certified performance results for the finalists.
Scientific distinction between food loss and waste and potential machine learning applications
The concepts of food loss and food waste are related but not identical; loss can arise during agricultural production, processing, and transportation stages, while waste often occurs near retail or final consumption, meaning that interventions addressing each may require separate evidence and data.
Machine learning applications in this sector can include demand forecasting, detecting quality changes using smart cameras or sensors, and preempting disruptions in storage or logistics operations. These points represent examples of technically feasible approaches rather than confirmations that Qassim University has launched those specific products.
Limits of innovative project maturity and stages of transition to actual production
The most significant methodological constraint lies in the level of project maturity; while a hackathon can help generate prototypes or promising ideas, mere participation does not prove that a solution is commercially viable, that national food waste totals have decreased, or that a machine learning model possesses accuracy in live operations. The submitted proposals, finalists, funded experiments, signed contracts, and production deployments are entirely separate indicators.
The importance of this event stems from the fact that food security authorities in the Kingdom of Saudi Arabia engage universities and innovators to address shortcomings that carry direct economic and environmental repercussions. Furthermore, the explicit artificial intelligence and data focus provides a documented link to the region’s applied artificial intelligence ecosystem, even if this announcement is smaller in scale than major data center investments.
Upcoming milestones to turn qualified ideas into field trials
Useful upcoming news milestones include publishing the concepts of the finalist teams, providing evidence of technical testing, announcing named field trials in cooperation with food producers or logistics companies, and measuring actual reductions in loss or waste percentages.
The report did not disclose any new financial value; therefore, the confirmed development on October 25 is the conclusion of an innovation event with a specific quantitative participation and a declared artificial intelligence connection, and it should not be presented as a complete national launch of an artificial intelligence-operated food security system.
Frequently asked questions
Question: How many ideas participated and qualified in the Qassim University hackathon?
Answer: The hackathon received more than 220 innovative ideas, with 50 projects qualifying for the closing ceremony, consisting of 25 in-person entries and 25 remote entries.
Question: What entities organized the hackathon and what is the associated national program?
Answer: It was organized by Qassim University’s Institute of Studies and Consulting Services in cooperation with the Saudi Food and Security Authority, in alignment with the National Program to Reduce Food Loss and Waste (Lidoom).
Question: What is the difference between food loss and food waste in the value chain?
Answer: Food loss typically occurs during production, processing, and transportation stages, while food waste occurs during retail and final consumption stages.
Question: Do the hackathon’s qualified projects represent commercially deployed systems in markets?
Answer: No, the qualified projects represent innovative ideas and prototypes, and turning them into operational systems requires subsequent technical testing, field trials, and commercial contracts.
