This talk provides a critical view on employing machine learning / deep learning methods in algorithmic trading. We highlight the particular challenges that we meet in this domain along with approaches to tackle some of these challenges in practice. Even though experience has shown that algorithmic trading using advanced machine learning can be successful, the crucial issue remains that predictive patterns utilizing market inefficiencies quickly become void as soon as competing market participants use them too. The conclusion is that the crucial advantage is - and has always been - to know more and to be faster than competitors.
Dr. Ulrich Bodenhofer
Chief Artificial Intelligence Officer at QUOMATIC.AI