---
title: "TensorLOB: Structure-Preserving Tensor Learning for Limit Order Book Forecasting"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.02866v1"
permalink: "https://feed.astralor.com/items/itm_1d242a1ecf7f60173536c71f"
published: "2026-11-02T10:03:43.000Z"
score: 56
channel: "tech"
tags: ["推理效率","TensorLOB","Structure-Preserving Tensor Learning","Limit Order Book","Forecasting The","LOB","Its"]
---

# TensorLOB: Structure-Preserving Tensor Learning for Limit Order Book Forecasting

## At a glance

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. …

## Key points

- 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.

## Full text

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.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_1d242a1ecf7f60173536c71f