LOB-Based Deep Learning Models for Stock Price Trend Prediction: A Benchmark Study

TL;DR

This benchmark study evaluates fifteen deep learning models for stock trend prediction using Limit Order Book data, revealing their limited robustness and generalizability in real-world scenarios.

Contribution

The paper introduces LOBCAST, an open-source framework for benchmarking deep learning models on LOB data, highlighting their performance limitations and providing a comprehensive evaluation.

Findings

All models show significant performance drops on new data.

Current models have limited real-world applicability.

The study provides a benchmark for future research.

Abstract

The recent advancements in Deep Learning (DL) research have notably influenced the finance sector. We examine the robustness and generalizability of fifteen state-of-the-art DL models focusing on Stock Price Trend Prediction (SPTP) based on Limit Order Book (LOB) data. To carry out this study, we developed LOBCAST, an open-source framework that incorporates data preprocessing, DL model training, evaluation and profit analysis. Our extensive experiments reveal that all models exhibit a significant performance drop when exposed to new data, thereby raising questions about their real-world market applicability. Our work serves as a benchmark, illuminating the potential and the limitations of current approaches and providing insight for innovative solutions.