Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units
arXiv:2105.10430
Abstract
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.
arXiv comment18 pages, 7 figures, and 7 tables
References in corpus (13)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Neural Machine Translation by Jointly Learning to Align and Translate
- Sequence to Sequence Learning with Neural Networks
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Effective Approaches to Attention-based Neural Machine Translation
- DeepLOB: Deep Convolutional Neural Networks for Limit Order Books
- Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysis
- Deep Learning for Portfolio Optimization
- Dissecting the Graphcore IPU Architecture via Microbenchmarking
- Model-based Reinforcement Learning for Predictions and Control for Limit Order Books
- Transformers for Limit Order Books
- DeepFolio: Convolutional Neural Networks for Portfolios with Limit Order Book Data