---
title: Improving Deep Learning of Alpha Term Structures from the Order Book
url: https://www.ml-quant.com/papers/ssrn/4770476/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4770476
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4770476
featured: 2024-03-27
citations: 3
topic: Trading, Microstructure & Execution
---


# Improving Deep Learning of Alpha Term Structures from the Order Book

The article evaluates the efficiency of four deep learning models in predicting high-frequency returns in equities, emphasizing the role of network structure, input choice, and time inclusion.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4770476
- Identifier: SSRN 4770476
- Released: 2024-03-23
- First featured: Quant Letter No. 42 (2024-03-27): https://www.ml-quant.com/issues/2024-03-27/
- Citations (Semantic Scholar): 3
- Published in: not yet
- Topic: Trading, Microstructure & Execution

## Related

- [Deep limit order book forecasting: a microstructural guide](https://www.ml-quant.com/papers/arxiv/2403.09267/): The research applies deep learning techniques to predict mid-price changes for NASDAQ-traded stocks, providing a framework to evaluate the feasibility of these predictions.
- [HLOB - Information Persistence and Structure in Limit Order Books](https://www.ml-quant.com/papers/arxiv/2405.18938/): A new deep learning model, HLOB, has been developed for predicting Limit Order Book mid-price changes, outperforming nine other models and offering new insights into information distribution in Limit Order Books.
- [Algorithmic and high-frequency trading problems for Semi-Markov and Hawkes jump-diffusion models](https://www.ml-quant.com/papers/arxiv/2409.12776/): The paper presents jump-diffusion models to understand limit order book data in algorithmic and high-frequency trading, offering optimal solutions for trading issues within a stochastic optimal control framework.
- [Estimation of an Order Book Dependent Hawkes Process for Large Datasets](https://www.ml-quant.com/papers/arxiv/2307.09077/): A new high-frequency trading model uses a Hawkes process and high-dimensional functions from the order book, capable of handling billions of data points and tested on four NYSE stocks.
- [Deep attentive survival analysis in limit order books: estimating fill probabilities with convolutional-transformers](https://www.ml-quant.com/papers/arxiv/2306.05479/): A deep learning method outperforms other approaches in estimating filltimes of limit orders.
- [Deep Learning Meets Queue-Reactive: A Framework for Realistic Limit Order Book Simulation](https://www.ml-quant.com/papers/arxiv/2501.08822/): The MDQR model, an advanced Queue-Reactive model, uses neural networks to understand complex market dependencies, making it useful for practical applications like strategy creation.