Personalized Dynamic Pricing with Machine Learning: High-Dimensional Features and Heterogeneous Elasticity

We consider a seller who can dynamically adjust the price of a product at the individual customer level, by utilizing information about customers’ characteristics encoded as a d-dimensional feature vector. We assume a personalized demand model, parameters of which depend on s out of the d features. The seller initially does not know the relationship between the customer features and the product demand but learns this through sales observations over a selling horizon of T periods. We prove that the seller’s expected regret, that is, the revenue loss against a clairvoyant who knows the underlying demand relationship, is at least of order [Formula: see text] under any admissible policy. We then design a near-optimal pricing policy for a semiclairvoyant seller (who knows which s of the d features are in the demand model) who achieves an expected regret of order [Formula: see text]. We extend this policy to a more realistic setting, where the seller does not know the true demand predictors, and show that this policy has an expected regret of order [Formula: see text], which is also near-optimal. Finally, we test our theory on simulated data and on a data set from an online auto loan company in the United States. On both data sets, our experimentation-based pricing policy is superior to intuitive and/or widely-practiced customized pricing methods, such as myopic pricing and segment-then-optimize policies. Furthermore, our policy improves upon the loan company’s historical pricing decisions by 47% in expected revenue over a six-month period. This paper was accepted by Noah Gans, stochastic models and simulation.

An Optimal Customized Pricing Strategy for Truckload Transportation

The impacts of optimal pricing are rarely explored when it comes to truckload transportation. In this study, the question of what price should be given to which customer and for what service characteristics are investigated for truckload transportation. Accordingly, customers' attitudes and responses to the bid price must be modeled, and their flexibility in regards to the price must be analyzed. Bid response function is developed, and logit model is considered. The bid response function is examined from two different perspectives: the first one is a general model by which all data is used, and the second one is the logit model by using partitioned data obtained by clustering customers. Logit model sensitivity analysis is applied. After developing bid response functions, non-linear optimization model is developed to determine the bid price. The developed model will contribute to the logistics companies' profit margins in the long term.