Tensor analysis improves limit order book prediction accuracy
TensorLOB: Structure-Preserving Tensor Learning for Limit Order Book Forecasting
Machine Learning
Summary
Financial markets have records of many orders to buy or sell stocks at different prices, called the limit order book (LOB). This data has many parts like time, price levels, and order types that create a complex structure. The authors developed TensorLOB, a method that keeps this complex structure intact using math tools called tensors, instead of simplifying it. This approach helps better predict future market movements, showing improved results on a common testing dataset.
What this means in practice
- •For financial traders: Improve forecasting accuracy of stock price movements by using a tensor-based model that respects market order data structure.
- •For quantitative analysts: Design trading algorithms that exploit the multi-dimensional structure of order book data for better prediction performance.
Authors
Yuxuan Gu, Danilo Mandic
Abstract
The limit order book (LOB) records outstanding buy and sell orders across multiple price levels. Its state evolves over time across market side, price level, and order attribute, naturally forming a multiway structure. However, existing LOB models typically flatten these dimensions into a matrix model, thus obscuring the existing structural relationships. Starting from first principles and the market-microstructure intuition of the LOB, we design TensorLOB to operate entirely in the tensor domain. TensorLOB uses mode-wise tensor contractions for feature extraction and directly contracts the learned representation with low-rank class-weight tensors for prediction, retaining the distinct roles of time, side, level, and attribute modes. Experiments on the FI-2010 benchmark show that TensorLOB achieves the highest accuracy, recall, and F1 score across all four evaluated horizons. This proof of concept highlights the potential of high-dimensional modelling of multi-way latent information intrinsic to financial markets, which has so far been largely overlooked.