Supporting Trading in Financial Markets by Means of DL Tools
Deep Learning (DL) is disclosing new possibilities to automate complex decision making, and Finance is one the field that can benefit more from that. The need for investment decisions to look at a wider range of information has driven the interest towards the application of DL in Finance, due to the capability of the new architectures to explore complex relationships within groups of information sources or between sources and the quality of decisions. In this presentation, we will focus on some aspects regarding the use of DL in trading systems. In particular we will report some research findings from our group regarding the use of non-linear encoders and embedders in order to distort the data space, long-short term memory for multivariate volatility prediction and for learning an algorithmic trading strategy, convolutional neural networks in price series analysis.
Luigi Troiano is professor of Artificial Intelligence, Data Science and Machine Learning at University of Sannio, Department of Engineering, Italy. His research is devoted to mathematical modelling and algorithm development with applications to Finance and other industries. His expertise is designing, experimenting and validating algorithms, along their implementation in software systems for industrial environments, including some large international companies. He is coordinator of Computational and Intelligent Systems Engineering Laboratory (CISELab) at University of Sannio, aimed at developing research in Big Data and Deep Learning.