{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T02:24:40Z","timestamp":1760149480381,"version":"build-2065373602"},"reference-count":52,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Union\u2014NextGenerationEU","award":["ECS0000038","CUP F53C22000430001","1056"],"award-info":[{"award-number":["ECS0000038","CUP F53C22000430001","1056"]}]},{"name":"Italian Ministry of University and Research (MUR)","award":["ECS0000038","CUP F53C22000430001","1056"],"award-info":[{"award-number":["ECS0000038","CUP F53C22000430001","1056"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Data"],"abstract":"<jats:p>Value at risk is a statistic used to anticipate the largest possible losses over a specific time frame and within some level of confidence, usually 95% or 99%. For risk management and regulators, it offers a solution for trustworthy quantitative risk management tools. VaR has become the most widely used and accepted indicator of downside risk. Today, commercial banks and financial institutions utilize it as a tool to estimate the size and probability of upcoming losses in portfolios and, as a result, to estimate and manage the degree of risk exposure. The goal is to obtain the average number of VaR \u201cfailures\u201d or \u201cbreaches\u201d (losses that are more than the VaR) as near to the target rate as possible. It is also desired that the losses be evenly distributed as possible. VaR can be modeled in a variety of ways. The simplest method is to estimate volatility based on prior returns according to the assumption that volatility is constant. Otherwise, the volatility process can be modeled using the GARCH model. Machine learning techniques have been used in recent years to carry out stock market forecasts based on historical time series. A machine learning system is often trained on an in-sample dataset, where it can adjust and improve specific hyperparameters in accordance with the underlying metric. The trained model is tested on an out-of-sample dataset. We compared the baselines for the VaR estimation of a day (d) according to different metrics (i) to their respective variants that included stock return forecast information of d and stock return data of the days before d and (ii) to a GARCH model that included return prediction information of d and stock return data of the days before d. Various strategies such as ARIMA and a proposed ensemble of regressors have been employed to predict stock returns. We observed that the versions of the univariate techniques and GARCH integrated with return predictions outperformed the baselines in four different marketplaces.<\/jats:p>","DOI":"10.3390\/data8080133","type":"journal-article","created":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T10:15:48Z","timestamp":1692267348000},"page":"133","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Leveraging Return Prediction Approaches for Improved Value-at-Risk Estimation"],"prefix":"10.3390","volume":"8","author":[{"given":"Farid","family":"Bagheri","sequence":"first","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124 Cagliari, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8646-6183","authenticated-orcid":false,"given":"Diego","family":"Reforgiato Recupero","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, University of Cagliari, Via Ospedale 72, 09124 Cagliari, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9239-2237","authenticated-orcid":false,"given":"Espen","family":"Sirnes","sequence":"additional","affiliation":[{"name":"School of Business and Economics, UiT The Arctic University of Norway, Breivangvegen 23, 9010 Troms\u00f8, Norway"}]}],"member":"1968","published-online":{"date-parts":[[2023,8,17]]},"reference":[{"key":"ref_1","unstructured":"Gallati, R.R. (2003). Risk Management and Capital Adequacy, McGraw-Hill."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.iimb.2012.09.001","article-title":"Evaluation of Basel III revision of quantitative standards for implementation of internal models for market risk","volume":"24","author":"Sharma","year":"2012","journal-title":"IIMB Manag. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1257\/jep.15.4.157","article-title":"GARCH 101: The Use of ARCH\/GARCH Models in Applied Econometrics","volume":"15","author":"Engle","year":"2001","journal-title":"J. Econ. Perspect."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"29942","DOI":"10.1109\/ACCESS.2021.3059187","article-title":"Ensembling and Dynamic Asset Selection for Risk-Controlled Statistical Arbitrage","volume":"9","author":"Carta","year":"2021","journal-title":"IEEE Access"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1007\/s10260-015-0332-9","article-title":"An exponentially weighted quantile regression via SVM with application to estimating multiperiod VaR","volume":"25","author":"Xu","year":"2016","journal-title":"Stat. Methods Appl."},{"key":"ref_6","first-page":"305","article-title":"Modelling daily value-at-risk using realized volatility, non-linear support vector machine and ARCH type models","volume":"3","author":"Khan","year":"2011","journal-title":"J. Econ. Int. Financ."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2541","DOI":"10.1162\/NECO_a_00647","article-title":"Extended robust support vector machine based on financial risk minimization","volume":"26","author":"Takeda","year":"2014","journal-title":"Neural Comput."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"61","DOI":"10.25103\/jestr.081.11","article-title":"Tail risk assessment using support vector machine","volume":"8","year":"2015","journal-title":"J. Eng. Sci. Technol. Rev."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"947","DOI":"10.1007\/s00180-019-00934-7","article-title":"Data driven value-at-risk forecasting using a SVR-GARCH-KDE hybrid","volume":"35","author":"Lux","year":"2020","journal-title":"Comput. Stat."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"080013","DOI":"10.1063\/5.0107539","article-title":"Value at risk estimation with hybrid-SVR-GARCH-KDE model for LQ45 portfolio optimization","volume":"2540","author":"Wara","year":"2023","journal-title":"AIP Conf. Proc."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1080\/09603100903459873","article-title":"Modelling commodity value at risk with higher order neural networks","volume":"20","author":"Dunis","year":"2010","journal-title":"Appl. Financ. Econ."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"316","DOI":"10.1080\/1351847X.2012.744763","article-title":"Modelling commodity value at risk with Psi Sigma neural networks using open\u2013high\u2013low\u2013close data","volume":"21","author":"Sermpinis","year":"2015","journal-title":"Eur. J. Financ."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.asoc.2016.08.003","article-title":"Quantile autoregression neural network model with applications to evaluating value at risk","volume":"49","author":"Xu","year":"2016","journal-title":"Appl. Soft Comput."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/j.econmod.2017.02.014","article-title":"Calculating Value-at-Risk for high-dimensional time series using a nonlinear random mapping model","volume":"67","author":"Zhang","year":"2017","journal-title":"Econ. Model."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.procs.2018.10.213","article-title":"Forecasting exchange rate value at risk using deep belief network ensemble based approach","volume":"139","author":"He","year":"2018","journal-title":"Procedia Comput. Sci."},{"key":"ref_16","unstructured":"Banhudo, G.S.F.D. (2019). Adaptive Value-at-Risk Policy Optimization: A Deep Reinforcement Learning Approach for Minimizing the Capital Charge. [PhD Thesis, ISCTE Business School]."},{"key":"ref_17","unstructured":"Yu, P., Lee, J.S., Kulyatin, I., Shi, Z., and Dasgupta, S. (2019). Model-based deep reinforcement learning for dynamic portfolio optimization. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"28920","DOI":"10.1109\/ACCESS.2023.3259108","article-title":"A Mean-VaR Based Deep Reinforcement Learning Framework for Practical Algorithmic Trading","volume":"11","author":"Jin","year":"2023","journal-title":"IEEE Access"},{"key":"ref_19","unstructured":"Li, Z., Tran, M.N., Wang, C., Gerlach, R., and Gao, J. (2020). A bayesian long short-term memory model for value at risk and expected shortfall joint forecasting. arXiv."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1016\/j.matcom.2022.07.015","article-title":"Encoded Value-at-Risk: A machine learning approach for portfolio risk measurement","volume":"202","author":"Arian","year":"2022","journal-title":"Math. Comput. Simul."},{"key":"ref_21","first-page":"3863107","article-title":"Construction and simulation of market risk warning model based on deep learning","volume":"2022","author":"Zhao","year":"2022","journal-title":"Sci. Program."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Blom, H.M., de Lange, P.E., and Risstad, M. (2023). Estimating Value-at-Risk in the EURUSD Currency Cross from Implied Volatilities Using Machine Learning Methods and Quantile Regression. J. Risk Financ. Manag., 16.","DOI":"10.20944\/preprints202305.0594.v1"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"47","DOI":"10.2469\/faj.v56.n2.2343","article-title":"Value at risk","volume":"56","author":"Linsmeier","year":"2000","journal-title":"Financ. Anal. J."},{"key":"ref_24","unstructured":"Alexander, C. (2009). Market Risk Analysis, Value at Risk Models, John Wiley & Sons."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"47","DOI":"10.2469\/faj.v52.n6.2039","article-title":"Risk2: Measuring the risk in value at risk","volume":"52","author":"Jorion","year":"1996","journal-title":"Financ. Anal. J."},{"key":"ref_26","unstructured":"Box, G.E., Jenkins, G.M., Reinsel, G.C., and Ljung, G.M. (2015). Time Series Analysis: Forecasting and Control, John Wiley & Sons."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1002\/fut.3990110204","article-title":"Risk premia and price volatility in futures markets","volume":"11","author":"Yoo","year":"1991","journal-title":"J. Futur. Mark."},{"key":"ref_28","unstructured":"Hyndman, R.J., and Athanasopoulos, G. (2018). Forecasting: Principles and Practice, OTexts."},{"key":"ref_29","first-page":"105","article-title":"The summation of random causes as the source of cyclic processes","volume":"5","author":"Slutzky","year":"1937","journal-title":"Econom. J. Econom. Soc."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Carta, S., Corriga, A., Ferreira, A., Recupero, D.R., and Saia, R. (2019). A Holistic Auto-Configurable Ensemble Machine Learning Strategy for Financial Trading. Computation, 7.","DOI":"10.3390\/computation7040067"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1080\/095400996116785","article-title":"On Combining Artificial Neural Nets","volume":"8","author":"Sharkey","year":"1996","journal-title":"Connect. Sci."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.inffus.2004.04.003","article-title":"Diversity in search strategies for ensemble feature selection","volume":"6","author":"Tsymbal","year":"2005","journal-title":"Inf. Fusion"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1016\/j.ejor.2006.05.029","article-title":"Improved customer choice predictions using ensemble methods","volume":"181","author":"Potharst","year":"2007","journal-title":"Eur. J. Oper. Res."},{"key":"ref_34","first-page":"1","article-title":"Gradient Boosting for Quantitative Finance","volume":"24","author":"Davis","year":"2020","journal-title":"J. Comput. Financ."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1016\/S0925-2312(03)00372-2","article-title":"Financial time series forecasting using support vector machines","volume":"55","year":"2003","journal-title":"Neurocomputing"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Sadorsky, P. (2021). A Random Forests Approach to Predicting Clean Energy Stock Prices. J. Risk Financ. Manag., 14.","DOI":"10.3390\/jrfm14020048"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1007\/s11408-001-0306-9","article-title":"VaR for nonlinear financial instruments-linear approximation or full Monte Carlo?","volume":"15","author":"Ammann","year":"2001","journal-title":"Financ. Mark. Portf. Manag."},{"key":"ref_38","first-page":"39","article-title":"Evaluation of value-at-risk models using historical data","volume":"2","author":"Hendricks","year":"1996","journal-title":"Econ. Policy Rev."},{"key":"ref_39","unstructured":"Damodaran, A. (2007). Strategic Risk Taking: A Framework for Risk Management, Wharton School Publishing. [1st ed.]."},{"key":"ref_40","unstructured":"Wiener, Z. (1999). Risk Management and Regulation in Banking: Proceedings of the International Conference on Risk Management and Regulation in Banking (1997), Springer."},{"key":"ref_41","unstructured":"Dowd, K. (1999). Beyond Value at Risk: The New Science of Risk Management, John Wiley & Son Limited."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/S0140-9883(02)00111-1","article-title":"Estimating oil price \u2018Value at Risk\u2019 using the historical simulation approach","volume":"25","author":"Cabedo","year":"2003","journal-title":"Energy Econ."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1056","DOI":"10.1016\/j.matcom.2021.05.029","article-title":"Portfolio Value-at-Risk and expected-shortfall using an efficient simulation approach based on Gaussian Mixture Model","volume":"190","author":"Seyfi","year":"2021","journal-title":"Math. Comput. Simul."},{"key":"ref_44","unstructured":"Morgan, J.P. (1996). RiskMetrics\u2014Technical Document, J.P. Morgan\/Reuters."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"50","DOI":"10.3905\/jod.1997.407974","article-title":"On the covariance matrices used in value at risk models","volume":"4","author":"Alexander","year":"1997","journal-title":"J. Deriv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"63","DOI":"10.3905\/jod.1997.407973","article-title":"Investigation of a class of volatility estimators","volume":"4","author":"Boudoukh","year":"1997","journal-title":"J. Deriv."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"771","DOI":"10.1080\/09603101003636188","article-title":"Forecasting accuracy of stochastic volatility, GARCH and EWMA models under different volatility scenarios","volume":"20","author":"Ding","year":"2010","journal-title":"Appl. Financ. Econ."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"73","DOI":"10.3905\/jod.1995.407942","article-title":"Techniques for verifying the accuracy of risk measurement models","volume":"3","author":"Kupiec","year":"1995","journal-title":"J. Deriv."},{"key":"ref_49","unstructured":"Haas, M. (2001). New Methods in Backtesting, Financial Engineering Research Center."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"841","DOI":"10.2307\/2527341","article-title":"Evaluating interval forecasts","volume":"39","author":"Christoffersen","year":"1998","journal-title":"Int. Econ. Rev."},{"key":"ref_51","first-page":"51","article-title":"Value-at-risk (VAR) estimation and backtesting during COVID-19: Empirical analysis based on BRICS and US stock markets","volume":"19","author":"Shaik","year":"2022","journal-title":"Invest. Manag. Financ. Innov."},{"key":"ref_52","unstructured":"Nieppola, O. (2009). Backtesting Value-at-Risk Models. [Master Thesis, Helsinki School of Economics]."}],"container-title":["Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5729\/8\/8\/133\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:36:03Z","timestamp":1760128563000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5729\/8\/8\/133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,17]]},"references-count":52,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,8]]}},"alternative-id":["data8080133"],"URL":"https:\/\/doi.org\/10.3390\/data8080133","relation":{},"ISSN":["2306-5729"],"issn-type":[{"type":"electronic","value":"2306-5729"}],"subject":[],"published":{"date-parts":[[2023,8,17]]}}}