The Market Fraction Hypothesis under Different GP Algorithms

Abstract

In a previous work, inspired by observations made in many agent-based financial models, we formulated\nand presented the Market Fraction Hypothesis, which basically predicts a short duration for any dominant\ntype of agents, but then a uniform distribution over all types in the long run. We then proposed a two-step\napproach, a rule-inference step, and a rule-clustering step, to test this hypothesis. We employed genetic\nprogramming as the rule inference engine, and applied self-organizing maps to cluster the inferred rules.\nWe then ran tests for 10 international markets and provided a general examination of the plausibility\nof the hypothesis. However, because of the fact that the tests took place under a GP system, it could be\nargued that these results are dependent on the nature of the GP algorithm. This chapter thus serves as\nan extension to our previous work. We test the Market Fraction Hypothesis under two new different GP\nalgorithms, in order to prove that the previous results are rigorous and are not sensitive to the choice\nof GP. We thus test again the hypothesis under the same 10 empirical datasets that were used in our\nprevious experiments. Our work shows that certain parts of the hypothesis are indeed sensitive on the\nalgorithm. Nevertheless, this sensitivity does not apply to all aspects of our tests. This therefore allows\nus to conclude that our previously derived results are rigorous and can thus be generalized.