University of Twente and the ING Group have put their signatures to a five-year collaboration agreement covering artificial intelligence and data science in the financial world. The partnership was celebrated at FinanceCom 2022, a leading-edge conference hosted by UT. It marks the first time that this international congress in finance and fintech has been held in the Netherlands. Jos van Hillegersberg, Professor of Business Information Systems at UT, and recently appointed Academic Director of Jheronimus Academy of Data Science, is looking forward to the collaboration between UT and ING. "We in the Netherlands have been pioneering and innovating applications involving artificial intelligence for quite some time. There are lots of opportunities in the financial sector. But we also ran into a problem: there's an enormous demand for talent in the business community and academic world. Our partnership will help alleviate this shortage. The fact that ING will be actively investing in UT's academic knowledge already says a lot."

Convolutional neural networks (CNN) and long short-term memory (LSTM) networks have become a staple of sequence learning. Due to the well-established fact that financial time series data exhibit exceptionally noisy characteristics, capital market anomalies are virtually impossible to detect. We deploy CNN networks for predicting out-of-sample stock movements for 200 high-volume European stocks from 1994 until 2014, and compare its overall performance with a modified LSTM model as in Fischer, Krauss (2017). Specifically, we compare empirical training and validation accuracies of both model architectures and reveal portfolio performance characteristics in terms of return and risk metrics for different portfolio sizes, trying to derive common patterns within the top and flop stocks. Thus, we unveil sources of long-term profitability and demonstrate, that both LSTM and CNN networks are able to extract meaningful information from such noisy financial time series.