Novel pricing strategies for revenue maximization and demand learning using an exploration–exploitation framework

Abstract

The price demand relation is a fundamental concept that models how price affects the sale of a product. It is critical to have an accurate estimate of its parameters, as it will impact the company's revenue. The learning has to be performed very efficiently using a small window of a few test points, because of the rapid changes in price demand parameters due to seasonality and fluctuations. However, there are conflicting goals when seeking the two objectives of revenue maximization and demand learning, known as the learn/earn trade-off. This is akin to the exploration/exploitation trade-off that we encounter in machine learning and optimization algorithms. In this paper, we consider the problem of price demand function estimation, taking into account its exploration-exploitation characteristic. We design a new objective function that combines both aspects. This objective function is essentially the revenue minus a term that measures the error in parameter estimates. Recursive algorithms that optimize this objective function are derived. The proposed method outperforms other existing approaches.

Optimizing Revenue Maximization and Demand Learning in Airline Revenue Management

“…Inspired by the work developed in [4], we present a novel method for jointly optimizing the revenue maximization and model learning under the monopolistic single leg airline RM problem. We show the effectiveness of our method under an unconstrained capacity assumption when estimating a single model parameter (price sensitivity).…”

“…More recently, a novel method [4] combines the revenue maximization and the accumulation of information into a single objective function as…”

“…This is one of the reasons why this problem attracted the attention from academia and industry in recent years. In one of the most recent and promising methods, the authors propose to unify revenue maximization and demand learning into one single objective function [4]. They find that their method outperforms several others in literature over simulation studies and different real-world benchmarks.…”

“…Then, in Section 3, we present some related work on the investigation of the earning while learning problem. Next, in Section 4, we demonstrate how to adapt the work [4] to the single leg problem, allowing their method to be applied to airline RM. Following, in Section 5, we present the experimental results comparing the adapted method to RMS in a simulation environment.…”

The application of artificial intelligence in health financing: a scoping review

“…AI can facilitate the implementation of dynamic strategies for revenue maximization through demand learning, which might result in lower out-of-pocket and impoverishment costs. The proposed method balances the trade-off between exploitation (revenue maximization) and exploration (demand model estimation) [ 52 ]. Utilizing methods such as Multi-Criteria Decision Analysis (MCDA) could facilitate the development of a decision support system in healthcare, thereby contributing to the efficient, rational, and fair allocation of resources [ 53 ].…”