Advanced search
Start date

Parameterizable algorithm for price optimization on brick and mortar retail products using Multi-Armed Bandit Algorithm (MAB) and Robust Quadratic Programming (RQP)


Pricing brick and mortar retail products is a challenge for retailers. The sheer amount of products and variables involved creates a difficulty in achieving optimal pricing, as stores have between 3,000 to 50,000 different products and the variables involved in calculating demand range from the selling price itself (which is the most representative) to day of the week, seasonality, weather, competition with other retailers, cannibalization and product affinity, among others. The objective of this research is the development of an optimized product pricing algorithm that increases margin or sales of a brick and mortar retailer in a parameterizable way (beta coefficient = weight between margin and sales). AMR Research studies show that the average potential for gross sales increases by 1 to 3% and gross margin by 2 to 5% for regular pricing optimization (excluding promotional and markdown prices). (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
Articles published in other media outlets (0 total):
More itemsLess items