Learning dynamic prices in MultiSeller electronic retail markets with price sensitive customers, stochastic demands, and inventory replenishments

Abstract

Abstract-In this paper, we use reinforcement learning (RL) as a tool to study price dynamics in an electronic retail market consisting of two competing sellers, and price sensitive and lead time sensitive customers. Sellers, offering identical products, compete on price to satisfy stochastically arriving demands (customers), and follow standard inventory control and replenishment policies to manage their inventories. In such a generalized setting, RL techniques have not previously been applied. We consider two representative cases: 1) no information case, were none of the sellers has any information about customer queue levels, inventory levels, or prices at the competitors; and 2) partial information case, where every seller has information about the customer queue levels and inventory levels of the competitors. Sellers employ automated pricing agents, or pricebots, which use RL-based pricing algorithms to reset the prices at random intervals based on factors such as number of back orders, inventory levels, and replenishment lead times, with the objective of maximizing discounted cumulative profit. In the no information case, we show that a seller who uses Q-learning outperforms a seller who uses derivative following (DF). In the partial information case, we model the problem as a Markovian game and use actor-critic based RL to learn dynamic prices. We believe our approach to solving these problems is a new and promising way of setting dynamic prices in multiseller environments with stochastic demands, price sensitive customers, and inventory replenishments.Index Terms-Dynamic pricing, inventory replenishments, markovian game, multi-agent learning, online retail markets, price sensitive customers, reinforcement learning (RL), stochastic demands.

Dynamic Pricing in Electronic Commerce Using Neural Network

“…However, some intelligent agents use a number of assumptions for the dynamic pricing in online markets. Some intelligent agents assume that sellers are provided with complete knowledge of market parameters, while some other agents consider product price as the only attribute that determines consumers' purchase decision [2,9,10,12,22]. In recent decades extensive research has been done in dynamic pricing.…”

“…Several analytical models have been developed for dynamic pricing in online economies [1,16,22,9,11,2]. The main aim behind dynamic pricing is to adjust the product price in order to capitalize sellers' revenue.…”

Wholesale Power Price Dynamics Under Transmission Line Limits: A Use of an Agent-Based Intelligent Simulator

“…Reinforcement learning was often incorporated into agents so that they could interact with a dynamic environment [6][7]. Such applications of the agent-based approach could be found in understanding various market behaviors [8][9]. The applicability was also found in power trading.…”

“…Thus, the adaptive behavior of each agent is visually summarized in Figure 3. All agents 9 are controlled by ISO whose market clearing process is summarized in Figure 2.…”

Multi-agent Cooperation Models by Reinforcement Learning (MCMRL)

“…These temporary computations might not give details of everything, but may still be able to construct for some part of the data. There are many real-world problems that engage more than one thing for maximization of results [2].Retailers have always encountered the difficulty of sale the right goods that would produce the highest income for them. Finding the right products for a buyer or a service is a difficult task.…”