Abstract: Market movement direction predictions should take many financial instruments simultaneously into account due to their correlations. This intrinsic complexity leads to thousands of possible features and thus it is appropriate for deep neural networks. We apply a feed forward network on thousands of features and we compare it with more advanced recurrent neural networks that combine convolutional layers for feature embedding within long-short-term-memory cells. We also consider a model that makes predictions a dynamic time horizon in the future based on the confidence of predictions. The models were evaluated on two data sets consisting of commodity futures and the other one on ETL’s. We found out that in the walk forward evaluation process the models tend to overfit and thus a new technique is introduced to cope with this phenomenon. Advanced models outperform feed forward based on prediction accuracy.
Bio: Diego Klabjan is a professor at Northwestern University, Department of Industrial Engineering and Management Sciences. He is also Founding Director, Master of Science in Analytics. After obtaining his doctorate from the School of Industrial and Systems Engineering of the Georgia Institute of Technology in 1999 in Algorithms, Combinatorics, and Optimization, in the same year he joined the University of Illinois at Urbana-Champaign. In 2007 he became an associate professor at Northwestern and in 2012 he was promoted to a full professor. His research is focused on machine learning, deep learning and analytics with concentration in finance, transportation, sport, and bioinformatics. Professor Klabjan has led projects with large companies such as Intel, Baxter, Allstate, AbbVie, FedEx Express, General Motors, United Continental, and many others, and he is also assisting numerous start-ups with their analytics needs. He is also a founder of Opex Analytics LLC.