Long short-term memory (LSTM) networks are a state-of-the-art technique for sequence learning. They are less commonly applied to financial time series predictions, yet inherently suitable for this domain. We deploy LSTM networks for predicting out-of-sample directional movements for the...

The advent of reinforcement learning (RL) in financial markets is driven by several advantages inherent to this field of artificial intelligence. In particular, RL allows to combine the "prediction" and the "portfolio construction" task in one integrated step, thereby closely aligning the...

We develop an agent-based model in which heterogeneous and boundedly rational agents interact by trading a risky asset at an endogenously set price. Agents are endowed with balance sheets comprising the risky asset as well as cash on the asset side and equity capital as well as debt on the...

We develop an agent-based model in which heterogeneous and boundedly rational agents interact by trading a risky asset at an endogenously set price. Agents are endowed with balance sheets comprising the risky asset as well as cash on the asset side and equity capital as well as debt on the...

We develop an agent-based model in which heterogenous and boundedly rational agents interact by trading a risky asset at an endogenously set price. Agents are endowed with balance sheets comprising the risky asset as well as cash on the asset side and equity capital as well as debt on the...