Searching for the Effective Bidding Strategy Using Parameter Tuning in Genetic Algorithm

Abstract

Online auctions play an important role in today's e-commerce for procuring goods. The proliferation of online auctions has caused the increasing need to monitor and track multiple bids in multiple auctions. An autonomous agent that exploits a heuristic decision making framework was developed to tackle the problem of bidding across multiple auctions with varying start and end time and with varying protocols (including English, Dutch and Vickrey). This flexible and configurable framework enables the agent to adopt varying tactics and strategies that attempt to ensure that the desired item is delivered in a manner consistent with the user's preferences. However, the proposed bidding strategy is based on four bidding constraints which is polynomial in nature such that there are infinite solutions that can be deployed at any point in time. Given this large space of possibilities, a genetic algorithm is employed to search offline for effective strategies in particular class of environment. The strategies that emerge from this evolution are then codified into the agent's reasoning behaviour so that it can select the most appropriate strategy to employ in its prevailing circumstances. In this paper, the parameters of the crossover and mutation are tuned in order to come up with an optimal rate for this particular environment. The proposed framework is implemented in a simulated marketplace environment and its effectiveness is empirically demonstrated. The relative performance of the evolved bidding strategies is discussed in this paper.