Forecasting stock volatility and value-at-risk based on temporal convolutional networks

Zhang, Chunxia; Li, Jun; Huang, Xing-Fang; Zhang, Jiangshe; Huang, Hua-Chuan

doi:10.1016/j.eswa.2022.117951

Cited by 23 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The OLCHWOA-LSTM model presented is an interesting study that deepens understanding of how LSTM technology contributes to research on RV. Research in the past has focused on optimizing LSTM hyperparameters using an exhaustive method [82][83][84], which had the shortcomings of being time-consuming and yielding poor results. This limitation has just been addressed in this study.…”

Section: Discussionmentioning

confidence: 99%

An Improved Whale Optimization Algorithm for Global Optimization and Realized Volatility Prediction

Wang,

et al. 2023

CMC

View full text Add to dashboard Cite

The original whale optimization algorithm (WOA) has a low initial population quality and tends to converge to local optimal solutions. To address these challenges, this paper introduces an improved whale optimization algorithm called OLCHWOA, incorporating a chaos mechanism and an opposition-based learning strategy. This algorithm introduces chaotic initialization and opposition-based initialization operators during the population initialization phase, thereby enhancing the quality of the initial whale population. Additionally, including an elite opposition-based learning operator significantly improves the algorithm's global search capabilities during iterations. The work and contributions of this paper are primarily reflected in two aspects. Firstly, an improved whale algorithm with enhanced development capabilities and a wide range of application scenarios is proposed. Secondly, the proposed OLCHWOA is used to optimize the hyperparameters of the Long Short-Term Memory (LSTM) networks. Subsequently, a prediction model for Realized Volatility (RV) based on OLCHWOA-LSTM is proposed to optimize hyperparameters automatically. To evaluate the performance of OLCHWOA, a series of comparative experiments were conducted using a variety of advanced algorithms. These experiments included 38 standard test functions from CEC2013 and CEC2019 and three constrained engineering design problems. The experimental results show that OLCHWOA ranks first in accuracy and stability under the same maximum fitness function calls budget. Additionally, the China Securities Index 300 (CSI 300) dataset is used to evaluate the effectiveness of the proposed OLCHWOA-LSTM model in predicting RV. The comparison results with the other eight models show that the proposed model has the highest accuracy and goodness of fit in predicting RV. This further confirms that OLCHWOA effectively addresses real-world optimization problems.

show abstract

Section: Discussionmentioning

confidence: 99%

An Improved Whale Optimization Algorithm for Global Optimization and Realized Volatility Prediction

Wang,

et al. 2023

CMC

View full text Add to dashboard Cite

show abstract

“…Value at Risk (VaR) stands out as a popular method employed in operational risk assessments [18]. VaR is a statistical technique that facilitates the measurement of the worst expected loss over a specifc period at a defned confdence level [19]. Despite the simplicity of the VaR concept, its calculation is not straightforward.…”

Section: Literature Reviewmentioning

confidence: 99%

Operational Risk Assessment for the Pollination Service with Apis mellifera Bees in Cashew Crops in Vichada, Colombia

Castro Mercado,

Bravo Bastidas,

Osorio Gómez

2024

International Journal of Forestry Research

View full text Add to dashboard Cite

The cashew tree relies heavily on the presence of pollinators during the peak receptivity of its flower to facilitate the transfer of pollen from the stamen to the stigma and ensure successful fruit production. Apis mellifera bees play a crucial role as intermediaries in the pollination process of the fruit, simultaneously extracting nectar and pollen from the flowers. The pollination service (PS) is susceptible to various risk factors that, if realized, could impact both the beekeeping industry and cashew production. This article aims to assess the operational risks associated with pollination service for Anacardium occidentale production in Vichada, Colombia, as a strategic measure to safeguard the business’s value. Drawing on expert opinions and relevant literature, nineteen risks were identified, encompassing threats such as fires, thefts, attacks by wild animals, unexpected rains, etc. Following the application of Failure Mode and Effects Analysis (FMEA), four risks were prioritized based on their severity and occurrence. Subsequently, Value at Risk (VaR) was employed for risk evaluation. The anticipated loss for the pollination service, resulting from these prioritized risks: 1, 9, 12 and 13, was quantified at $226674 ± $19096 per year for an 8000-hectare margin with a confidence level of 95%. The economic loss for 16000 hectares was $453348 ± $38192. This substantial value is of great significance to the beekeeping sector, translating to a loss of $27.3 per hectare per year and directly impacting the estimated $437824 loss in the cashew sector. Such losses have far-reaching consequences, affecting the livelihoods of peasant beekeepers in the region and potentially discouraging the maintenance of bee colonies and forests.

show abstract

“…Yu and Li (2018) and Liu (2019) found that the forecasting capability of the deep learning model outperformed those of the classical machine learning models and econometric models. Additionally, convolution neural network (CNN) and its variations, such as temporal CNN, which is commonly used in image recognition, were applied for volatility forecasting by Doering et al (2017) and Zhang et al (2022).…”

Section: Introductionmentioning

confidence: 99%

Volatility forecasting for stock market incorporating media reports, investors' sentiment, and attention based on MTGNN model

Lei,

Song

2024

Journal of Forecasting

View full text Add to dashboard Cite

In this paper, the self‐monitoring learning model FinBERT is used to identify text emotions, and the sliding time window time‐lagged cross‐correlation (WTLCC) method is utilized to screen Baidu Index keywords for the Shanghai Stock Exchange Index and 18 A‐share listed companies. There are five different types of indicators constructed: news media sentiment, public attention, investor sentiment, investor sentiment disagreement, and media sentiment disagreement. To accurately describe the structure of sentimental contagion, this paper combines graph neural network to learn and output the sentimental contagion graph, and then constructs multivariable time series forecasting with graph neural networks (MTGNN) volatility forecasting model, which can extract the spatial–temporal dependence of variables in pairs. The results show that MTGNN model possesses the highest forecasting accuracy, which performs 30.30% lower on average across four evaluation indicators for Shanghai Stock Exchange Index than temporal pattern attention–long short‐term memory model, which ranks second. For all of the models considered in this paper, adding sentimental contagion mechanism can significantly improve the volatility forecasting accuracy. The error of MTGNN is reduced the most, with a 15.21% average reduction for the Shanghai Stock Exchange Index. The contagion relationship among media reports, investor sentiment, and attention can help provide new ideas for enhancing the precision of volatility forecasting from the public opinion environment in the financial market.

show abstract

Forecasting stock volatility and value-at-risk based on temporal convolutional networks

Cited by 23 publications

References 38 publications

An Improved Whale Optimization Algorithm for Global Optimization and Realized Volatility Prediction

An Improved Whale Optimization Algorithm for Global Optimization and Realized Volatility Prediction

Operational Risk Assessment for the Pollination Service with Apis mellifera Bees in Cashew Crops in Vichada, Colombia

Volatility forecasting for stock market incorporating media reports, investors' sentiment, and attention based on MTGNN model

Contact Info

Product

Resources

About