Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units
This addresses forecasting challenges in financial markets, offering incremental improvements in long-horizon predictions and training efficiency.
The paper tackles multi-horizon forecasting for limit order books using deep learning encoder-decoder models with attention, achieving comparable performance to state-of-the-art at short horizons and outperforming them at long horizons, while using Intelligent Processing Units (IPUs) to significantly speed up training times compared to GPUs.
We design multi-horizon forecasting models for limit order book (LOB) data by using deep learning techniques. Unlike standard structures where a single prediction is made, we adopt encoder-decoder models with sequence-to-sequence and Attention mechanisms to generate a forecasting path. Our methods achieve comparable performance to state-of-art algorithms at short prediction horizons. Importantly, they outperform when generating predictions over long horizons by leveraging the multi-horizon setup. Given that encoder-decoder models rely on recurrent neural layers, they generally suffer from slow training processes. To remedy this, we experiment with utilising novel hardware, so-called Intelligent Processing Units (IPUs) produced by Graphcore. IPUs are specifically designed for machine intelligence workload with the aim to speed up the computation process. We show that in our setup this leads to significantly faster training times when compared to training models with GPUs.