Can online trading algorithms beat the market? An experimental evaluation

Abstract

From experimental evaluation, we reasonably infer that online trading algorithms can beat the market. We consider the scenario of trading in financial market and present an extensive experimental study to answer the question "Can online trading algorithms beat the market?". We evaluate the selected set of online trading algorithms on DAX30 and measure the performance against buy-and-hold strategy. In order to compute the experimentally achieved competitive ratio, we also compare the set of algorithms against an optimum offline algorithm. To add further dimensionality into experimental setup, we use trading periods of various lengths and apply a number of evaluation criteria (such as annualized geometric returns, average period returns and experimentally achieved competitive ratio) to measure the performance of algorithms in short vs. Long term investment decisions. We highlight the best and worst performing algorithms and discuss the possible reasons for the performance behavior of algorithms.