Crude oil price forecasting: Experimental evidence from wavelet decomposition and neural network modeling

Jammazi, Rania; Aloui, Chaker

doi:10.1016/j.eneco.2011.07.018

Cited by 237 publications

(79 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Yu et al (2008); Xiong et al (2013) proposes an empirical mode based on the decomposition of neural networks to forecast crude oil prices. Jammazi and Aloui (2012) uses a hybrid model for crude oil forecasting, Panella et al (2012) use a mixture of gaussian neural network to forecast energy commodity prices, and Papadimitriou et al (2014) investigates the efficiency of a support vector machines in forecasting next day electricity prices. Moreover, focus is placed solely on the forecasting of prices, whereas research using neural networks to forecast volatility is still being developed.…”

Section: Introductionmentioning

confidence: 99%

Coupling High-Frequency Data with Nonlinear Models in Multiple-Step-Ahead Forecasting of Energy Markets' Volatility

Baruník

Křehlík

2014

SSRN Journal

View full text Add to dashboard Cite

Standard-Nutzungsbedingungen:Die Dokumente auf EconStor dürfen zu eigenen wissenschaftlichen Zwecken und zum Privatgebrauch gespeichert und kopiert werden.Sie dürfen die Dokumente nicht für öffentliche oder kommerzielle Zwecke vervielfältigen, öffentlich ausstellen, öffentlich zugänglich machen, vertreiben oder anderweitig nutzen.Sofern die Verfasser die Dokumente unter Open-Content-Lizenzen (insbesondere CC-Lizenzen) zur Verfügung gestellt haben sollten, gelten abweichend von diesen Nutzungsbedingungen die in der dort genannten Lizenz gewährten Nutzungsrechte. Abstract: Terms of use: Documents inIn the past decade, the popularity of realized measures and various linear models for volatility forecasting has attracted attention in the literature on the price variability of energy markets. However, results that would guide practitioners to a specifc estimator and model when aiming for the best forecasting accuracy are missing. This paper contributes to the ongoing debate with a comprehensive evaluation of multiple-step-ahead volatility forecasts of energy markets using several popular high-frequency measures and forecasting models. To capture the complex patterns hidden to linear models commonly used to forecast realized volatility, this paper also contributes to the literature by coupling realized measures with artificial neural networks as a forecasting tool. Forecasting performance is compared across models as well as realized measures of crude oil, heating oil, and natural gas volatility during three qualitatively distinct periods covering the precrisis period, recent global turmoil of markets in 2008, and the most recent post-crisis period. We conclude that coupling realized measures with arti_cial neural networks results in both statistical and economic gains, reducing the tendency to over-predict volatility uniformly during all tested periods. Our analysis favors the median realized volatility, as it delivers the best performance and is a computationally simple alternative for practitioners.

show abstract

Section: Introductionmentioning

confidence: 99%

Coupling High-Frequency Data with Nonlinear Models in Multiple-Step-Ahead Forecasting of Energy Markets' Volatility

Baruník

Křehlík

2014

SSRN Journal

View full text Add to dashboard Cite

show abstract

“…For commodities product, discrete wavelet transform (DWT) based method exists in forecasting of crude oil price [12], oil price [13], and natural gas price [14] that are the most interesting products in views of many researchers. There also has a work for forecasting metal prices that consists of aluminum, copper, lead, and zinc [15].…”

Section: B Wavelet Transform In Commodities Price Time Series Forecamentioning

confidence: 99%

Multiresolution Analysis Based on Wavelet Transform for Commodity Prices Time Series Forecasting

Bunrit¹,

Kerdprasop²,

Kerdprasop³

2018

IJMLC

View full text Add to dashboard Cite

Abstract-This research proposes time series forecasting of commodity prices by using multiresolution analysis from wavelet transform. In this work, discrete wavelet transform based multiresolution decomposition of Deubechies family is used. Firstly, Deubechies wavelet transform is applied to the training set of time series data up to level four. The reconstruction values of the approximation part of wavelet from each level are then used for the forecasting process by ARIMA model. The validation set of data is used to analyze and select the best model from all 4 levels of multiresolution decomposition. Finally, best selected validating model is used for evaluating the remaining testing data set. The forecasting results by using multiresolution analysis are compared to the case where the original data are directly modeled and forecasted by ARIMA. Results based on the mean absolute percentage error evaluation from using multiresolution analysis are better for both of the two studied data including daily gold price and rubber price. By applying multiresolution analysis, the improvement is 10.83% for gold price and 42.68% for rubber price. The variances of errors from the proposed method on both data sets are also much less than directly use the original time series data for forecasting.

show abstract

“…At the same time H. White [2] and the authors of recent studies, for example, R. Jammazi and S. Aloui [3], N.A. Valiotti and V.L.…”

mentioning

confidence: 99%

“…He demonstrates the high predictive power of a neural network to forecast of the financial instruments behavior in his later works, for example [3]. The advantages of a neural network in comparison with the classical time series models such as ARIMA include the ability to model time series forecast automatically, the lack of subjectivity in choosing the best model, flexibility and nonlinearity, etc.…”

mentioning

confidence: 99%

“…For the analyzed time period, we collect information on such fundamentals as the S&P500 index and DAX index, exchange rate for Russian ruble to US dollar and Brent crude oil price 2 . In addition, we use information from websites of Central Bank of Russia 3 and US Department of Treasury 4 on the dynamics of 1-month Moscow Interbank Offered Rate and 3-month Treasury Bill rates respectively. We select technical and fundamental indicators taking into account that they are frequently used in prior research; they have the ability to explain the behavior of individual indicators of Russian stock market that previously found in the literature [8; 9]; we are able to calculate them for the current research data.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Micex Index Forecasting: The Predictive Power of Neural Network Modeling and Support Vector Machine

Lozinskaia

Zhemchuzhnikov

2017

Вестник ПГУ. Сер. Эконом.

View full text Add to dashboard Cite

The ability to predict the dynamics of financial instruments is an important topic for financial market players. In the context of large and heterogeneous information, there is a need to use effective methods to data processing for management decision-making. In particular, machine learning techniques are becoming very popular in financial modeling. The aim of this paper is to forecast the Russian stock price index by using machine learning methods such as neural network modeling and support vector machine and to examine their predictive power. For economic and mathematical modeling, we use statistical and analytical information on the dynamics of the MICEX stock price index, fundamental and technical indicators of the stock market for the period 2002-2016 years. For computational experiments, we use training, testing and validation datasets and software for machine learning in Python. The predictive power of the methods is estimated on the validation data with using both traditional indicators of mathematical statistics (such as absolute and relative prediction error) and count coefficient of determination. We found the use of a longer time period for the MICEX index that corresponds to large training data set in neural network modeling has led to training error reduction. The predictive power of support vector machine on validation data set is higher comparing with neural network modeling. However, that difference in prediction metrics is not significant. The development of a methodology for filtering input data and trading strategy based on machine learning algorithms are possible directions for further research.Keywords Возможность прогнозирования динамики финансовых инструментов представляет собой актуальную задачу для участников финансового рынка. В условиях большого потока разнородной информации возникает потребность в использовании эффективных методов их обработки для выработки оперативных управленческих решений. В частности, все большее распространение в финансовом моделировании получают методы машинного обучения. Цель работы заключается в моделировании прогноза российского биржевого индекса с помощью таких методов машинного обучения, как метод нейросетевого моделирования и метод опорных векторов, и исследовании их предсказательной силы. Информационную базу экономико-математического моделирования составили статистические и аналитические данные о динамике индекса ММВБ, фундаментальных и технических индикаторов фондового рынка за 2002-2016 гг. Результаты компьютерных экспериментов выполнены на обучающей, тестирующей и подтверждающей выборке c использованием соответствующих библиотек машинного обучения на языке Python. Оценка предсказательной силы методов осуществлялась на подтверждающей выборке с использованием традиционных показателей математической статистики (абсолютной и относительной ошибки прогноза) и счетного коэффициента детерминации. Установлено, что использование более длительного временного промежутка для индекса ММВБ и, соответственно, большего числа наблюдений, при обучении нейронной сети спо...

show abstract

Crude oil price forecasting: Experimental evidence from wavelet decomposition and neural network modeling

Cited by 237 publications

References 35 publications

Coupling High-Frequency Data with Nonlinear Models in Multiple-Step-Ahead Forecasting of Energy Markets' Volatility

Coupling High-Frequency Data with Nonlinear Models in Multiple-Step-Ahead Forecasting of Energy Markets' Volatility

Multiresolution Analysis Based on Wavelet Transform for Commodity Prices Time Series Forecasting

Micex Index Forecasting: The Predictive Power of Neural Network Modeling and Support Vector Machine

Contact Info

Product

Resources

About