Research On The Fluctuation Network Evolution And Prospective Behavior Judgement Of U.S. Heating Oil Prices

In the northeast of America,heating oil is an indispensable heating fuel,and its price tends to fluctuate over time,which makes it difficult for ordinary families to effectively manage and purchase.Thus,studying the volatility and related laws of heating oil spot and futures markets can help to quantify some uncertain factors and provide scientific theoretical evidence for avoiding risks in markets.In addition,price risk is the focus of risk control research in the heating oil futures market,it is equally important to analyze and predict the trend of price fluctuations.This paper mainly focuses on the following aspects:(1)The complex network model of price fluctuations is established.First of all,this paper conducts coarse grained treatment on selected data of heating oil spot and futures prices.Then,its price fluctuation sequence is transformed into a corresponding symbol sequence.Furthermore,based on the processing results of the above data,the period of volatility is divided according to the proportion of price fluctuations,and several network models of heating oil price fluctuations in different periods are set up.(2)The evolution rules of heating oil price fluctuation networks are analyzed.First,this paper studies some static geometric quantities of the network,such as the average path length,strength and intensity distribution of nodes,betweenness and clustering coefficients.Then,the transition cycle of price fluctuation modes in the network,the time distribution feature about the appearance of important modes,the evolution of those intermediate modes,and the clustering characteristics between the wave modes are discussed respectively from the perspective of the whole and sub-periods.Finally,this paper starts with the cumulative time interval of new nodes,and examines the regularity of the emergence of new nodes.The results show that both the heating oil spot price fluctuation network and futures price fluctuation network show a highly line growth trend,whether it is in the period of severe volatility or stable volatility.In addition,this paper constructs a similarity measurefunction from the perspective of network nodes,calculates the similarity of two networks,and finds that the similarity of the above two networks is higher from the overall point of view;from the point of view of sub-periods,both the correlation is extremely weak within the sharp fluctuations,but it is highly correlated during the stable fluctuation period.(3)A novel time series prediction model combined with the complex network method is put forward.First of all,this paper counts the cumulative time interval of different nodes in the network,and fits its growth trend with the Fourier model.Then,a novel price fluctuation prediction model is established based on the effective information such as some topology properties extracted from the network.The results show that the Fourier model can predict the emergence time of new nodes in the next stage,and the established price fluctuation prediction model can infer the names of nodes in the prediction interval,so as to determine the forward-looking behavior of price evolution.Besides,liken to the NAR neural network,the prediction results obtained by the proposed method also show superiority,which has important theoretical value and academic significance for early warning and prediction of price behavior in the heating oil futures market.