The Accuracy of Linear Models in Stock Price Volatility Prediction: An Investigation and Comparison with Artificial Intelligence Approaches

Stock volatility forecasting is always crucial for investors and stock owners to make financial decisions, portfolio allocation, and risk management. Even though there are a lot of popular volatility forecasting models existing in the stock market, it is hard to know which one was the best depending on different situations in the market. And so, this review examines the accuracy of linear models in forecasting stock price volatility, and evaluates the performance of these models compared with relatively complicated nonlinear and artificial-intelligence-based approaches. The review analyzes previous studies on major volatility forecasting models, including ARCH, GARCH, ARIMA, and HAR-RV. It compares findings from traditional linear models with more recent research on nonlinear models, machine learning, and artificial intelligence. In addition, the review also considers how forecasting performance changes across different markets, forecasting horizons, and market conditions. The reviewed evidence showed that linear models remain competitive because they are interpretable, computationally efficient, and effective when capturing persistent volatility patterns. Recent studies indicate that machine-learning models do not consistently outperform linear models in every situation, although AI approaches may provide advantages when financial relationships are more complex or when additional data are available. Overall, this review concludes that greater model complexity does not automatically lead to a higher forecasting accuracy. Future volatility prediction may benefit from hybrid and regime-aware models that combine the transparency of linear approaches with the flexibility of artificial intelligence.

Authors

Publication Details

Journal
Advances in Economics Management and Political Sciences
Published
2026-11-17
DOI
https://doi.org/10.54254/2754-1169/2026.ld39005
Primary Topic
Financial Risk and Volatility Modeling
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

The Accuracy of Linear Models in Stock Price Volatility Prediction: An Investigation and Comparison with Artificial Intelligence Approaches

Chin Yu Ching David
1 links
Advances in Economics Management and Political Sciences
Financial Risk and Volatility Modeling
article

The Accuracy of Linear Models in Stock Price Volatility Prediction: An Investigation and Comparison with Artificial Intelligence Approaches

Chin Yu Ching David
article en

Abstract

Stock volatility forecasting is always crucial for investors and stock owners to make financial decisions, portfolio allocation, and risk management. Even though there are a lot of popular volatility forecasting models existing in the stock market, it is hard to know which one was the best depending on different situations in the market. And so, this review examines the accuracy of linear models in forecasting stock price volatility, and evaluates the performance of these models compared with relatively complicated nonlinear and artificial-intelligence-based approaches. The review analyzes previous studies on major volatility forecasting models, including ARCH, GARCH, ARIMA, and HAR-RV. It compares findings from traditional linear models with more recent research on nonlinear models, machine learning, and artificial intelligence. In addition, the review also considers how forecasting performance changes across different markets, forecasting horizons, and market conditions. The reviewed evidence showed that linear models remain competitive because they are interpretable, computationally efficient, and effective when capturing persistent volatility patterns. Recent studies indicate that machine-learning models do not consistently outperform linear models in every situation, although AI approaches may provide advantages when financial relationships are more complex or when additional data are available. Overall, this review concludes that greater model complexity does not automatically lead to a higher forecasting accuracy. Future volatility prediction may benefit from hybrid and regime-aware models that combine the transparency of linear approaches with the flexibility of artificial intelligence.

Advances in Economics Management and Political SciencesVol. 314(1)
Financial Risk and Volatility Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon