A Deep Learning Framework for High-Frequency Signal Forecasting Based on Graph and Temporal-Macro Fusion

With the increase in trading frequency and the growing complexity of data structures, traditional quantitative strategies have gradually encountered bottlenecks in modeling capacity, real-time responsiveness, and multi-dimensional information integration. To address these limitations, a high-frequen...

Full description

Saved in:
Bibliographic Details
Main Authors: Xijue Zhang, Liman Zhang, Siyang He, Tianyue Li, Yinke Huang, Yaqi Jiang, Haoxiang Yang, Chunli Lv
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/9/4605
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849312751146500096
author Xijue Zhang
Liman Zhang
Siyang He
Tianyue Li
Yinke Huang
Yaqi Jiang
Haoxiang Yang
Chunli Lv
author_facet Xijue Zhang
Liman Zhang
Siyang He
Tianyue Li
Yinke Huang
Yaqi Jiang
Haoxiang Yang
Chunli Lv
author_sort Xijue Zhang
collection DOAJ
description With the increase in trading frequency and the growing complexity of data structures, traditional quantitative strategies have gradually encountered bottlenecks in modeling capacity, real-time responsiveness, and multi-dimensional information integration. To address these limitations, a high-frequency signal generation framework is proposed, which integrates graph neural networks, cross-scale Transformer architectures, and macro factor modeling. This framework enables unified modeling of structural dependencies, temporal fluctuations, and macroeconomic disturbances. In predictive validation experiments, the framework achieved a precision of 92.4%, a recall of 91.6%, and an F1-score of 92.0% on classification tasks. For regression tasks, the mean squared error (MSE) and mean absolute error (MAE) were reduced to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.76</mn><mo>×</mo><msup><mn>10</mn><mrow><mo>−</mo><mn>4</mn></mrow></msup></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.96</mn><mo>×</mo><msup><mn>10</mn><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></semantics></math></inline-formula>, respectively. These results significantly outperformed several mainstream models, including LSTM, FinBERT, and StockGCN, demonstrating superior stability and practical applicability.
format Article
id doaj-art-cbbafc442d7d4aebbeed886bdac40b18
institution Kabale University
issn 2076-3417
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-cbbafc442d7d4aebbeed886bdac40b182025-08-20T03:52:57ZengMDPI AGApplied Sciences2076-34172025-04-01159460510.3390/app15094605A Deep Learning Framework for High-Frequency Signal Forecasting Based on Graph and Temporal-Macro FusionXijue Zhang0Liman Zhang1Siyang He2Tianyue Li3Yinke Huang4Yaqi Jiang5Haoxiang Yang6Chunli Lv7China Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaChina Agricultural University, Beijing 100083, ChinaWith the increase in trading frequency and the growing complexity of data structures, traditional quantitative strategies have gradually encountered bottlenecks in modeling capacity, real-time responsiveness, and multi-dimensional information integration. To address these limitations, a high-frequency signal generation framework is proposed, which integrates graph neural networks, cross-scale Transformer architectures, and macro factor modeling. This framework enables unified modeling of structural dependencies, temporal fluctuations, and macroeconomic disturbances. In predictive validation experiments, the framework achieved a precision of 92.4%, a recall of 91.6%, and an F1-score of 92.0% on classification tasks. For regression tasks, the mean squared error (MSE) and mean absolute error (MAE) were reduced to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.76</mn><mo>×</mo><msup><mn>10</mn><mrow><mo>−</mo><mn>4</mn></mrow></msup></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>0.96</mn><mo>×</mo><msup><mn>10</mn><mrow><mo>−</mo><mn>2</mn></mrow></msup></mrow></semantics></math></inline-formula>, respectively. These results significantly outperformed several mainstream models, including LSTM, FinBERT, and StockGCN, demonstrating superior stability and practical applicability.https://www.mdpi.com/2076-3417/15/9/4605deep learning in quantitative schemesignal forecastinggraph neural networksattention mechanism
spellingShingle Xijue Zhang
Liman Zhang
Siyang He
Tianyue Li
Yinke Huang
Yaqi Jiang
Haoxiang Yang
Chunli Lv
A Deep Learning Framework for High-Frequency Signal Forecasting Based on Graph and Temporal-Macro Fusion
Applied Sciences
deep learning in quantitative scheme
signal forecasting
graph neural networks
attention mechanism
title A Deep Learning Framework for High-Frequency Signal Forecasting Based on Graph and Temporal-Macro Fusion
title_full A Deep Learning Framework for High-Frequency Signal Forecasting Based on Graph and Temporal-Macro Fusion
title_fullStr A Deep Learning Framework for High-Frequency Signal Forecasting Based on Graph and Temporal-Macro Fusion
title_full_unstemmed A Deep Learning Framework for High-Frequency Signal Forecasting Based on Graph and Temporal-Macro Fusion
title_short A Deep Learning Framework for High-Frequency Signal Forecasting Based on Graph and Temporal-Macro Fusion
title_sort deep learning framework for high frequency signal forecasting based on graph and temporal macro fusion
topic deep learning in quantitative scheme
signal forecasting
graph neural networks
attention mechanism
url https://www.mdpi.com/2076-3417/15/9/4605
work_keys_str_mv AT xijuezhang adeeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT limanzhang adeeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT siyanghe adeeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT tianyueli adeeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT yinkehuang adeeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT yaqijiang adeeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT haoxiangyang adeeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT chunlilv adeeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT xijuezhang deeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT limanzhang deeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT siyanghe deeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT tianyueli deeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT yinkehuang deeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT yaqijiang deeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT haoxiangyang deeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion
AT chunlilv deeplearningframeworkforhighfrequencysignalforecastingbasedongraphandtemporalmacrofusion