Management Review ›› 2021, Vol. 33 ›› Issue (9): 25-37.

• Economic and Financial Management • Previous Articles     Next Articles

The Study for Characteristics of Commodity (Rebar) Futures Price Trend Based on Stochastic Search Approach

George Xianzhi Yuan1,2,3, Di Lan4, Song Guandu5, Zhou Yunpeng3, Liu Haiyang3, Guoqi Qian6, Yan Chengxing3, Zeng Tu3   

  1. 1. Business School, Chengdu University, Chengdu 610106;
    2. Business School, Sun Yat-Sen University, Guangzhou 510275;
    3. BBD Technology Co., Ltd. (BBD), Chengdu 610093;
    4. School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi 214122;
    5. The University of New South Wales:High St, Kensington, New South Wales 2052, Australia;
    6. School of Mathematics and Statistics, The University of Melbourne, Melbourne VIC3010, Australia
  • Received:2020-01-09 Online:2021-09-28 Published:2021-10-09

Abstract: The goal of this paper is to develop a way to show how we extract related characteristic factors (features) related to the price trend of commodity futures for screw steel materials by applying Gibbs sampling algorithm under the framework of Markov chain Monte Carlo (MCMC), then classify features related to the price trend of commodity futures into different levels by using the concept of the odds ratio associated with logistic regression model. Our empirical analysis results show that the feature extraction method discussed in this paper can effectively describe the trend of rebar futures price, which provides a new analysis method for bulk futures trading business, risk hedging and related risk management in the practice of financial industry. In addition, the method discussed to extract highly related effective characteristic factors that affect the change of price trend is also different from those in existing literature for the analysis of trend of price change.

Key words: commodity futures, price trend, related features, Markov Chain Monte Carlo, Akaike Information Criterion & Bayesian Information Criterion