2013 | OriginalPaper | Chapter
A Comparative Study of Heuristic Conversion Algorithms, Genetic Programming and Return Predictability on the German Market
Authors : Esther Mohr, Günter Schmidt, Sebastian Jansen
Published in: EVOLVE- A Bridge between Probability, Set Oriented Numerics and Evolutionary Computation
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
This paper evaluates the predictability of the heuristic conversion algorithms
Moving Average Crossover
and
Trading Range Breakout
in the German stock market. Hypothesis testing and a bootstrap procedure are used to test for predictive ability. Results show that the algorithms considered do not have predictive ability. Further,
Genetic Programming
is used to adapt the buying and selling rules of the investigated algorithms resulting in a new algorithm. Results show that a genetic programming approach does not lead to good new algorithms. We extend former works by using the
Sortino Ratio
as a measure of risk, and by applying competitive analysis.