mlsanityData to 7 Oct 2026

Multi-Horizon Forecasting for Limit Order Books: Novel Deep Learning Approaches and Hardware Acceleration using Intelligent Processing Units

arXiv 2105.10430 ↗First posted 21 May 2021cs.LG cs.NE q-fin.TRcited by 10

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 18 of its 39 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

18 of 39 references.

References · 18

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,024
  7. 2016TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systemscited by 660
  8. 2019Deep Reinforcement Learning for Tradingcited by 73
  9. 2018Universal features of price formation in financial markets: perspectives from Deep Learningcited by 59
  10. 2017Benchmark Dataset for Mid-Price Forecasting of Limit Order Book Data with Machine Learning Methodscited by 49
  11. 2019Dissecting the Graphcore IPU Architecture via Microbenchmarkingcited by 47
  12. 2017Temporal Attention augmented Bilinear Network for Financial Time-Series Data Analysiscited by 46
6 more
  1. 2018Using Deep Learning for price prediction by exploiting stationary limit order book featurescited by 27
  2. 2021Deep Reinforcement Learning for Active High Frequency Tradingcited by 21
  3. 2019Model-based Reinforcement Learning for Predictions and Control for Limit Order Bookscited by 14
  4. 2020Deep Learning modeling of Limit Order Book: a comparative perspectivecited by 11
  5. 2021Deep Learning for Market by Order Datacited by 8
  6. 2020DeepFolio: Convolutional Neural Networks for Portfolios with Limit Order Book Datacited by 2

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 4; 2024: 1; 2025: 1.

10 papers.

  1. 2023LOB-Based Deep Learning Models for Stock Price Trend Prediction: A Benchmark Studycited by 9
  2. 2021Realised Volatility Forecasting: Machine Learning via Financial Word Embeddingcited by 7
  3. 2024Deep Limit Order Book Forecastingcited by 7
  4. 2022Axial-LOB: High-Frequency Trading with Axial Attentioncited by 4
  5. 2023Transformers versus LSTMs for electronic tradingcited by 4
  6. 2025TLOB: A Novel Transformer Model with Dual Attention for Price Trend Prediction with Limit Order Book Datacited by 4
  7. 2023Asynchronous Deep Double Duelling Q-Learning for Trading-Signal Execution in Limit Order Book Marketscited by 3
  8. 2023Market Making with Deep Reinforcement Learning from Limit Order Bookscited by 1
  9. 2021NanoBatch Privacy: Enabling fast Differentially Private learning on the IPUcited by 0
  10. 2022Accelerating Machine Learning Training Time for Limit Order Book Predictioncited by 0