Work
Each case below follows the same shape: the decision at stake, my role, the data and its constraints, the approach, how it was evaluated, what it produced and where it falls short. Industry delivery, doctoral research and an independently scored competition are labelled as such.
Designing and building a forecasting and procurement decision-support system for a UK packaging e-commerce business, covering more than 1,200 products, as the KTP Associate on a partnership between Priory Direct and the University of Kent.
Read the case study: From demand forecasts to procurement decisions →Doctoral research on attended home delivery for online grocery, where forecasts of orders still to come are used to decide which delivery slots to offer, what to charge for them and how to route the vans. Published in the European Journal of Operational Research and Annals of Operations Research.
Read the case study: Using forecast demand to improve delivery decisions →VN2 was the first public inventory-planning competition. Over six consecutive weekly rounds, participants placed orders for 599 product–store combinations with a two-week lead time, scored on holding and shortage cost. I finished sixth of around 180 participants; the organiser reports that only 25 entries beat his benchmark of a seasonally weighted moving average with a fixed stock target.
Unlike the industry work, the competition data and scoring are public, so the result is independent evidence that I can turn forecasts into ordering decisions under asymmetric holding and shortage costs.
Organiser's results announcement →I am open to data science and optimisation roles, research collaboration and, in time, independent projects. If the problems above look like yours, a short note is enough to start a conversation.
Get in touch