Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive models

In financial production systems, accurate risk prediction is crucial for decision- makers. Traditional forecasting methods face certain limitations when dealing with complex time-series data and nonlinear dependencies between systems, especially under extreme market fluctuations. To address this, we...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuduo Lin, Ziang Qi 
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-07-01
Series:Frontiers in Physics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphy.2025.1627551/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850084087197335552
author Xuduo Lin
Ziang Qi 
author_facet Xuduo Lin
Ziang Qi 
author_sort Xuduo Lin
collection DOAJ
description In financial production systems, accurate risk prediction is crucial for decision- makers. Traditional forecasting methods face certain limitations when dealing with complex time-series data and nonlinear dependencies between systems, especially under extreme market fluctuations. To address this, we propose an innovative hybrid temporal model, TSA-AR (Temporal Self-Attention Adaptive Autoregression), which combines temporal self-attention mechanisms with an adaptive autoregressive model to solve the risk prediction problem in financial and production systems. TSA-AR performs multi-scale feature extraction through an improved Informer encoder, dynamically adjusts model parameters with a dynamic autoregressive module, and constructs the nonlinear dependencies between financial and production systems through a cross_modal interaction graph. Experimental results show that TSA-AR achieves an MSE of 0.0689, significantly lower than other comparative models (e.g., Transformer’s 0.0921), and performs excellently with an Extreme Risk Detection Rate of 81.70%. The model effectively improves the accuracy and stability of risk prediction, providing a more accurate forecasting tool for financial-production system risk management, with significant practical implications.
format Article
id doaj-art-9a970cc8cee14a6ea4ab34db25e56315
institution DOAJ
issn 2296-424X
language English
publishDate 2025-07-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Physics
spelling doaj-art-9a970cc8cee14a6ea4ab34db25e563152025-08-20T02:44:08ZengFrontiers Media S.A.Frontiers in Physics2296-424X2025-07-011310.3389/fphy.2025.16275511627551Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive modelsXuduo Lin0Ziang Qi 1School of Environment, Education and Development, University of Manchester, Manchester, United KingdomDuke University, Durham, NC, United StatesIn financial production systems, accurate risk prediction is crucial for decision- makers. Traditional forecasting methods face certain limitations when dealing with complex time-series data and nonlinear dependencies between systems, especially under extreme market fluctuations. To address this, we propose an innovative hybrid temporal model, TSA-AR (Temporal Self-Attention Adaptive Autoregression), which combines temporal self-attention mechanisms with an adaptive autoregressive model to solve the risk prediction problem in financial and production systems. TSA-AR performs multi-scale feature extraction through an improved Informer encoder, dynamically adjusts model parameters with a dynamic autoregressive module, and constructs the nonlinear dependencies between financial and production systems through a cross_modal interaction graph. Experimental results show that TSA-AR achieves an MSE of 0.0689, significantly lower than other comparative models (e.g., Transformer’s 0.0921), and performs excellently with an Extreme Risk Detection Rate of 81.70%. The model effectively improves the accuracy and stability of risk prediction, providing a more accurate forecasting tool for financial-production system risk management, with significant practical implications.https://www.frontiersin.org/articles/10.3389/fphy.2025.1627551/fullrisk predictiontemporal self-attentionadaptive autoregression modelcross-modal interaction graphfinancial-production system
spellingShingle Xuduo Lin
Ziang Qi 
Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive models
Frontiers in Physics
risk prediction
temporal self-attention
adaptive autoregression model
cross-modal interaction graph
financial-production system
title Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive models
title_full Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive models
title_fullStr Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive models
title_full_unstemmed Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive models
title_short Dynamic risk prediction in financial-production systems using temporal self-attention and adaptive autoregressive models
title_sort dynamic risk prediction in financial production systems using temporal self attention and adaptive autoregressive models
topic risk prediction
temporal self-attention
adaptive autoregression model
cross-modal interaction graph
financial-production system
url https://www.frontiersin.org/articles/10.3389/fphy.2025.1627551/full
work_keys_str_mv AT xuduolin dynamicriskpredictioninfinancialproductionsystemsusingtemporalselfattentionandadaptiveautoregressivemodels
AT ziangqi dynamicriskpredictioninfinancialproductionsystemsusingtemporalselfattentionandadaptiveautoregressivemodels