Evolving Bidding Strategies using Self Adaptation

Online auctions play an important role in today’s e-commerce for procuring goods. The proliferation of online auctions has caused the increasing need of monitoring and tracking multiple bids in multiple auctions. This paper investigates the application of self adaptive genetic algorithms on a flexible and configurable heuristic decision making framework that can tackle the problem of bidding across multiple auctions that apply different protocols (English, Vickrey and Dutch) by using an autonomous agent to search for the most effective strategies (offline). Genetic algorithm has shown promising results in searching in large and little priori information space but our study shows that self adaptive genetic algorithm is able to perform better than genetic algorithm in many cases. An empirical evaluation on the effectiveness of genetic algorithm and self adaptive genetic algorithm for searching the most effective strategies in the heuristic decision making framework are discussed in this paper.