A hybrid method for crude oil price direction forecasting using multiple timeframes dynamic time wrapping and genetic algorithm

Xiang, Youtao; Fu, Zhe; Wang, Mingyue; Wang, Yueren

doi:10.1016/j.asoc.2019.105566

Cited by 19 publications

(5 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At least for the update and prediction period of the model, researchers rely on the stationarity and weakly stationarity hypotheses. Such kind of models usually found in literature, include artificial neural networks (ANN), Neural Nets and support vector machine models (Bashiri Behmiri & Pires Manso, 2013; Karasan et al, 2018; Kulkarni & Haidar, 2009; Xie et al, 2006; Yin & Wang, 2019; Yu et al, 2008). The reader who needs a more extensive review on all types of statistical and advanced informatics models can use the work of Bashiri Behmiri & Pires Manso (2013).…”

Section: Literature Reviewmentioning

confidence: 99%

Strategic alignment of pricing oil products from Brent conditionally on market regimes using Markov and cluster‐based switching dynamics

Theodorou

Apokoritis²

2022

OPEC Energy Review

View full text Add to dashboard Cite

Refiners face a key economic trade off among flexibility and cost strategy in order to attain strategic alignment (Theodorou, 1996;Theodorou & Karyampas, 2008). The tradeoff is whether to pay a price premium for higher grades (procurement rigidity) or accept to pay higher capex and refining costs in order to take advantage of lower grades (procurement flexibility). Costs and payback periods must be weighed against anticipated prices and the projected differential or price spread among oil products. Flexibility strategy refers to the alignment of operations to the continuous changes of crude oil prices and the prices of refined products. Thus, crude slate and refinery's complexity must be aligned with the states, regimes reflected in the prices of both crude oil and the products of distillation. Crude oil prices can determine the states or regimes of the market and play a very significant role in pricing and energy policy. Refiners have limited range of flexibility in setting the gasoline to distillate production ratio. According to refinery economics and shifting yields, diesel along with gasoline is of primary focus as high value lights versus residuals (lowest-value by-product).Moreover, the significance of the price states, regimes is derived by the oil's market share and its mark-to-market use in energy contracts, as it is applied in the pricing formulas of most fossil fuels and energy products (Jammazi &

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Strategic alignment of pricing oil products from Brent conditionally on market regimes using Markov and cluster‐based switching dynamics

Theodorou

Apokoritis²

2022

OPEC Energy Review

View full text Add to dashboard Cite

show abstract

“…Apart from the standard operations for the genetic algorithm (as described in Section 2), it also offers an opportunity for immigration (i.e., the substitution of given chromosomes between populations). Similarly, Deng et al (2019) employed a genetic algorithm to the dynamic time wrapping method and forecasted the directional movements of the Brent and WTI prices. The obtained hit ratio of their forecasts was an average of 70%, which was around 40% more than in the case of the benchmark methods.…”

Section: Energy Commoditiesmentioning

confidence: 99%

A Review of the Applications of Genetic Algorithms to Forecasting Prices of Commodities

Drachal

Pawłowski

2021

Economies

View full text Add to dashboard Cite

This paper is focused on the concise review of the specific applications of genetic algorithms in forecasting commodity prices. Genetic algorithms seem relevant in this field for many reasons. For instance, they lack the necessity to assume a certain statistical distribution, and they are efficient in dealing with non-stationary data. Indeed, the latter case is very frequent while forecasting the commodity prices of, for example, crude oil. Moreover, growing interest in their application has been observed recently. In parallel, researchers are also interested in constructing hybrid genetic algorithms (i.e., joining them with other econometric methods). Such an approach helps to reduce each of the individual method flaws and yields promising results. In this article, three groups of commodities are discussed: energy commodities, metals, and agricultural products. The advantages and disadvantages of genetic algorithms and their hybrids are presented, and further conclusions concerning their possible improvements and other future applications are discussed. This article fills a significant literature gap, focusing on particular financial and economic applications. In particular, it combines three important—yet not often jointly discussed—topics: genetic algorithms, their hybrids with other tools, and commodity price forecasting issues.

show abstract

“…DTW was first proposed and applied to spoken word recognition in 1978 [2] and has been used in pattern recognition [23], time-series data processing [24][25][26][27], signature verification [28,29], speech segment clustering [30], exceptional motion capture [31], etc. It was first used to obtain the optimal alignment between points in both template sequences and test sequences, calculating the distance to obtain two sequences aligned and judge whether two sequences are similar.…”

Section: Dynamic Time Warpingmentioning

confidence: 99%

A Novel Time-Sensitive Composite Similarity Model for Multivariate Time-Series Correlation Analysis

Liang

Wang

2021

Entropy

View full text Add to dashboard Cite

Finding the correlation between stocks is an effective method for screening and adjusting investment portfolios for investors. One single temporal feature or static nontemporal features are generally used in most studies to measure the similarity between stocks. However, these features are not sufficient to explore phenomena such as price fluctuations similar in shape but unequal in length which may be caused by multiple temporal features. To research stock price volatilities entirely, mining the correlation between stocks should be considered from the point view of multiple features described as time series, including closing price, etc. In this paper, a time-sensitive composite similarity model designed for multivariate time-series correlation analysis based on dynamic time warping is proposed. First, a stock is chosen as the benchmark, and the multivariate time series are segmented by the peaks and troughs time-series segmentation (PTS) algorithm. Second, similar stocks are screened out by similarity. Finally, the rate of rising or falling together between stock pairs is used to verify the proposed model’s effectiveness. Compared with other models, the composite similarity model brings in multiple temporal features and is generalizable for numerical multivariate time series in different fields. The results show that the proposed model is very promising.

show abstract

A hybrid method for crude oil price direction forecasting using multiple timeframes dynamic time wrapping and genetic algorithm

Cited by 19 publications

References 20 publications

Strategic alignment of pricing oil products from Brent conditionally on market regimes using Markov and cluster‐based switching dynamics

Strategic alignment of pricing oil products from Brent conditionally on market regimes using Markov and cluster‐based switching dynamics

A Review of the Applications of Genetic Algorithms to Forecasting Prices of Commodities

A Novel Time-Sensitive Composite Similarity Model for Multivariate Time-Series Correlation Analysis

Contact Info

Product

Resources

About