Event Details

A pair of talks on clearing stock.

First Talk

Anna-Lena Sachs

Title: Making smart recommendations for perishable and stockout products

Joint work with: Sinan Seymen and Edward C. Malthouse (Northwestern University, USA)

Abstract:

Food waste and stockouts are widely recognized as an important global challenge. While inventory management aims to address these challenges, the tools available to inventory managers are often limited and the usefulness of their decisions is dependent on demand realizations, which are not within their control. Recommender systems (RS) can influence and direct customer demand, e.g.,

by sending personalized emails with promotions for different items. We propose a novel approach that combines the opportunities provided by RS with inventory management considerations. Under the assumption that there is a known set of customers to receive a promotion consisting of 𝑘 items, we use mixed-integer programming (MIP) to allocate recommended items across customers taking

both individual preferences and the current state of inventory with uncertainties into account. Our approach can solve problems with both stochastic supply (inventory and perishability) and demand. We propose heuristics to improve scalability and compare their performance with the optimal solution using data from an online grocery retailer. The goal is to target the right set of customers

who are likely to purchase an item, while simultaneously considering which items are prone to expire or be out-of-stock soon. We show that creating recommendation lists exclusively considering user preferences can be counterproductive to users due to possible excessive stockouts. Similarly, focusing only on the retailer can be counterproductive to retailer sales due to the number of expired

products that can be considered lost income. We thus avoid the loss of customer goodwill due to stockouts and reduce waste by selling inventory before it expires.

Second Talk

David Leslie

Title: Adaptive discounting

Abstract:

The first talk in this session being an example of some of our interdisciplinary work connecting recommender systems, optimisation and inventory management, we will continue with discussing another interdisciplinary topic on learning about demand distributions in the presence of price discounts and inventory considerations in the second half of the session.

Towards the end of a product life-cycle, a supplier may also wish to offer discounted prices to clear the stock. This must be carried out carefully so as not to give away all the stock too quickly, but also not to be left with lots of stock that did not sell; the problem can be solved using backward induction if the sale distributions are known. However, to further complicate matters, we do not know how discounts will affect sales distributions until we observe the outcomes of some discounting events. I will present very preliminary work on solving this problem using a combination of Thompson sampling, modelling, and dynamic programming. This is very much a `work in progress’ seminar, and there will be lots of opportunities to suggest improvements!

Please attend in person - if that is not possible you can use the Teams link