Combining Evolutionary Computing Techniques to Find Credible Qualitative Descriptions of the Demand-Side of Markets

In many markets, customer preferences depend on the activity of the customer. The authors have previously demonstrated a model that allows the testing of the qualitative judgments of domain experts in spirits markets against relevant EPOS price and sales data. This paper extends the use of context dependent customer preferences to the case where domain experts lack confidence in their judgments or the judgments are found not to be in accordance with the data. We describe here an algorithm to produce credible alternative models for the domain experts to confirm or develop in light of their wider domain expertise. The algorithm combines random search, genetic programming and evolutionary hill-climbing techniques. We report the results of tests using data from a market for alcoholic beverages. The algorithm enables the automatic production of qualitative descriptions which are both consistent with observed data and deemed credible by the domain experts. The combination of these techniques is more robust and produces better results than any of these techniques separately