President's Medal

The President’s Medal is one of The OR Society’s most prestigious awards, and we’re inviting entries for the competition.

The President’s Medal is awarded for the best practical application of OR submitted to the competition (a wide definition of OR is used). Entries are welcomed from both industry based OR workers and consultants as well as from academics. One of the main qualifications for entry is that the work has been implemented before submission. If you’re thinking of giving a case study based paper at our annual conference, why not consider aiming a bit higher and going for the President’s Medal?

Criteria for judging include:

• The level of demonstrable benefit
• The intellectual and novel content of the solution
• The likely longevity of the solution
• The excellence of the OR process

Citation for President's Medal 2022

The Tesco data science team, led by Dr Ramon Fuentes (Lead Data Scientist)

Clearance Pricing Optimisation for UK’s Largest Supermarket.

The President’s Medal has been awarded for a project that combined technical expertise in a solution that delivered both the necessary scale, speed and variety of application, and has been seen through to full implementation into operational systems. The issue of balancing the need to maximise revenue whilst minimising waste is seen in both food and non-food items, and in both seasonal and non-seasonal goods. The scale of the solution is impressive enough in itself, with more than half a million pricing decisions across more than 3,000 UK stores being made daily.

The clearance optimisation problem is handled as a Markov decision process, with a series of interlinked demand forecasting and optimisation steps. The team had to overcome two sides to the optimisation challenge – the sheer number of decisions presented a computational challenge and having to optimise over fundamentally uncertain estimates which propagates further over the stages. This is book-ended with familiar challenges of bringing all the necessary data together and implementing the final models into store systems.

The results were impressive too. The initial trials in the Summer of 2019 were positive, but the second phase was able to deliver increased revenue and reduced waste. Whilst the total financial impact wasn’t shared (being highly sensitive, of course), the improvements in the levels of waste were 3-7% and that clearly represents significant savings. There are knock-on effects for the local communities too, with a much more accurate forecast of the amount of goods to be donated to food banks and other projects.

The project involved combining different approaches based on soft systems and lean service improvement methodologies. It ensured that core OR techniques were at the heart of evaluation processes that brought together service providers and users (in the form of patients). The combination of excellence of process, technical challenge, impressive impact and the longevity of the solution made this project a worthy winner in the judges’ eyes, mirroring the sentiment of the audience at the conference.

The team:

Ekaterina Arafailova, Francesco Bucci, Tim Butler, George Dikas, Sivaji Doguparthi, Ramon Fuentes, Ross Hart, Akshay Kishan, Can Kocer, Aleksandar Kolev, Sebastian Lautz, Stephen Logan, Fabio Milano, Edwin Reynolds, Himanshu Singh, Stephen Spurri, Hamish Teagle, Benjamin White, Da Wei Wong.