img

QQ群聊

img

官方微信

高级检索

黄金科学技术 ›› 2020, Vol. 28 ›› Issue (1): 148-157.doi: 10.11872/j.issn.1005-2518.2020.01.067

• 采选技术与矿山管理 • 上一篇    下一篇

基于商空间的黄金价格SVM模型预测

韩旭(),杨珊(),王喜梅   

  1. 中南大学资源与安全工程学院,湖南 长沙 410083
  • 收稿日期:2019-06-05 修回日期:2019-11-14 出版日期:2020-02-29 发布日期:2020-02-26
  • 通讯作者: 杨珊 E-mail:531865317@qq.com;yangshan@csu.edu.cn
  • 作者简介:韩旭(1995-),男,陕西宝鸡人,硕士研究生,从事矿业经济和采矿系统工程研究工作。531865317@qq.com
  • 基金资助:
    国家自然科学基金青年基金项目“基于人工智能的矿山技术经济指标动态优化”(51404305);国家自然科学基金项目“基于属性驱动的矿体动态建模及更新方法研究”(51504286);中国博士后科学基金面上项目“辰州矿业采掘计划可视化编制与优化研究”(2015M 572269);湖南省科技计划项目“辰州矿业采掘计划可视化编制与优化研究”(2015RS4060)

Modelling SVM and Prediction of Gold Price Based on Quotient Space

Xu HAN(),Shan YANG(),Ximei WANG   

  1. School of Resources and Safety Engineering,Central South University,Changsha 410083,Hunan,China
  • Received:2019-06-05 Revised:2019-11-14 Online:2020-02-29 Published:2020-02-26
  • Contact: Shan YANG E-mail:531865317@qq.com;yangshan@csu.edu.cn

摘要:

结合商空间理论和支持向量机方法,根据黄金价格的价格因子对我国黄金价格进行预测。采用Person相关系数法,对现阶段黄金价格的9个价格因子与黄金价格的相关性进行比较,筛选出相关系数较大的5个价格因子,并通过Granger因果检验,得出可能导致黄金价格变化的2个价格因子;将Person相关系数法和Granger因果检验选出的7个因子作为黄金价格预测的主要价格因子,结合商空间理论,按照时间属性,将黄金价格论域划分为年、季、月3个粒度,建立3层商空间,并进行粒度的合成和计算。然后建立基于商空间理论的支持向量机预测模型,预测得出年、季、月粒度的黄金价格预测值分别为8 122.4,7 947.506和8 089.5元/金衡盎司,合成结果为8 053.1元/金衡盎司。将预测结果与GM(1,1)预测值和实际黄金价格进行对比,证明该模型的预测结果在误差允许范围内,优于传统的价格预测方法。

关键词: 黄金价格, 影响因子, 商空间, 粒度, SVM模型, Person相关系数法, Granger因果检验

Abstract:

Based on the detailed analysis of the influencing factors of the gold price,the gold price of China was predicted according to the price factor of gold price combined with the quotient space theory and the support vector machine method.Firstly,we used the person correlation coefficient method to compare the correlation between 9 price factors with gold price in the current.Five price factors with larger correlation coefficient were selected,they are US dollar index,WIT crude oil futures,G5 currency index,producer index,consumer index and correlation coefficient with correlation coefficient of -0.46,0.52,0.5,0.59 and 0.55 respectively.Secondly,through the granger causality test,we got the reason that the commodity index and the consumer price of the index lead to the change of the gold price hypotheses are more likely to be established,the odds are 0.83338 and 0.95609 respectively.Then,using the dollar index,the WIT crude oil futures,the G5 currency index,the producer index,the consumer index,the commodity index and the consumer price index as the main price factors for the forecast,combining with the quotient space theory and according to the time attribute,divided the gold price domain into three divisions of year,quarter and month,then established the three-tier quotient space,and conducted the granularity of the synthesis and calculation.The SVM forecasting model based on the quotient space theory was established to forecast the gold price.The forecast value of the gold price for year,quarter and month granularity is 8 122.4 CNY/troy ounce,7 947.506 CNY/troy ounce and 8 089.5 CNY/troy ounce respectively,and the composite result is 8 053.1 CNY/troy ounce.Finally,the reliability of the model is verified by comparing the gold price forecast with the GM(1,1) forecast of 9 382.2 CNY/troy ounce and the actual gold price of 8 306.0 CNY/troy ounce,indicate that the prediction result of the model is within the range allowed by the error,and the model is superior to traditional price prediction methods..

Key words: gold price, influencing factor, quotient space, granularity, SVM model, Person correlation coefficient method, Granger causality test

中图分类号: 

  • X751

图1

2006~2015年各国黄金价格趋势图注:资料来源于世界黄金协会"

图2

2006~2015年黄金价格、CRB、CPI和WIT原油期货价格趋势对比注:资料来源于www.opce.com,www.crbtrader.com,www.imf.org"

图3

2006~2015年黄金价格、美元指数和G5货币指数趋势对比注:资料来源于世界黄金协会"

表1

价格因子及说明"

价格因子说明
CRB(x1商品指数:一种期货价格指数,总体上反映了世界主要商品价格的动态信息。在一定程度上揭示未来宏观经济的走向,能较好地反映通货膨胀
CPI(x2居民消费价格指数:反映居民家庭一般所购买的消费商品和服务价格水平变动情况的宏观经济指标
USDX(x3美元指数:综合反映美元在国际外汇市场的汇率情况的指标,用来衡量美元对一揽子货币的汇率变化程度
DJIA(x4道琼斯股票价格平均指数:是世界上最有影响、使用最广的股价指数,由4种股价平均指数构成。本文所述的是道琼斯指数中的第一组道琼斯工业平均指数(Dow Jones Industrial Average)
WTI(x5原油期货:取世界原油市场的三大价格基准之一的WTI原油价格
IR(x6通胀率:即通货膨胀率(Inflation Rate),是货币超发部分与实际需要的货币量之比,用以反映通货膨胀和货币贬值的程度
G5CI(x7G5货币指数(G5 Currency Index):是由G5货币,美元、欧元、日元、英镑和加元组成的指数,以3年GDP加权
PI(x8生产者指数(Produce Index):是由5个最大的黄金生产国货币组成的指数,按3年平均矿产量排名并加权,当前五大黄金生产国依次为中国、美国、俄罗斯、澳大利亚和南非
CI(x9消费者指数(Consumer Index):是由5种最大的黄金消费国货币组成的指数,按3年平均黄金需求量排序并加权
GP(y中国的黄金价格

表2

价格因子与黄金价格归一化数据"

年份x1x2x3x4x5x6x7x8x9y
20060.750.920.84-0.30-1.42-0.67-1.10-1.13-1.05-1.43
20070.520.62-0.06-0.03-0.590.93-0.91-1.03-1.00-1.18
20081.531.36-0.72-1.52-0.751.46-0.88-0.94-0.93-0.78
2009-1.09-1.73-0.31-0.97-0.72-1.74-0.76-0.78-0.80-0.47
2010-0.36-0.26-0.35-0.59-0.540.20-0.49-0.43-0.500.38
20110.840.92-1.18-0.38-0.251.22-0.120.03-0.041.35
20120.120.11-0.70-0.090.50-0.140.430.580.541.55
2013-0.18-0.33-0.511.071.220.150.921.011.040.59
2014-0.17-0.260.041.481.59-0.671.361.291.350.13
2015-1.93-1.362.331.350.96-0.721.571.401.39-0.14

表3

价格因子与黄金价格的相关系数"

x1x2x3x4x5x6x7x8x9y
x110.95-0.69-0.52-0.450.72-0.57-0.54-0.53-0.11
x20.951-0.54-0.38-0.400.79-0.46-0.44-0.43-0.11
x3-0.69-0.5410.440.11-0.600.310.230.25-0.46
x4-0.52-0.380.4410.85-0.300.870.850.870.21
x5-0.45-0.400.110.851-0.170.960.960.960.52
x60.720.79-0.60-0.30-0.171-0.25-0.23-0.240.13
x7-0.57-0.460.310.870.96-0.2510.9910.50
x8-0.54-0.440.230.850.96-0.230.99110.59
x9-0.53-0.430.250.870.96-0.241110.55
y-0.11-0.11-0.460.210.520.130.500.590.551

表4

Granger因果关系检验结果"

序号假设可能性Pr序号假设可能性Pr
1x1y的原因0.833388yx1的原因0.59425
2x2y的原因0.956099yx2的原因0.63112
3x3y的原因0.8760910yx3的原因0.99394
4x5y的原因0.0063911yx5的原因0.09528
5x7y的原因0.0016112yx7的原因0.14256
6x8y的原因0.0018013yx8的原因0.14409
7x9y的原因0.0003314yx9的原因0.13109

图4

黄金价格与价格因子粒度图"

表5

黄金价格SVM模型参数选优"

预测模型cgamma最优
月粒度1000.00787400.2661497
季粒度1000.02127660.2580292
年粒度1000.02127660.2275999

表6

2016年黄金价格预测值比较"

预测模型预测值/(元·金衡盎司-1相对误差δ/%
年粒度8 122.4δ=-2.21
季粒度7 947.5δ=-4.32
月粒度8 089.5δ=-2.61
GM(1,1)年均预测值9 382.2δGM=12.96
本文合成预测值8 053.1δ=-3.04
1 姚琳娜.影响黄金价格的因素分析[D].济南:山东大学,2015.
Yao Linna. Analysis of the Factors Influencing the Price of Gold[D].Jinan:Shandong University,2015.
2 王荣.国际黄金价格的影响因素及走势分析[D].济南:山东财经大学,2014.
Wang Rong.The Influence Factors of the International Price of Gold and Trend Analysis[D].Jinan:Shandong University of Finance and Economics,2014.
3 张勇.国际黄金价格的影响因素研究[D].成都:西南财经大学,2014.
Zhang Yong.Research on the Influential Factors of International Gold Price[D].Chengdu:Southwestern University of Finance and Economics,2014.
4 张晓丽.黄金价格影响因素的实证分析[D].昆明:昆明理工大学,2013.
Zhang Xiaoli.An Empirical Analysis of the Influencing Factors of the Gold Price[D].Kunming:Kunming University of Science and Technology,2013.
5 Kanjilal K,Sajal G.Dynamics of crude oil and gold price post 2008 global financial crisis-New evidence from threshold vector error-correction model[J].Resources Policy,2017,52:358-365.
6 Gil-Alana L,Yaya O S,Awe O O.Time series analysis of co-movements in the prices of gold and oil:Fractional cointegration approach[J].Resources Policy,2017,53:117-124.
7 Kamran A,Israr S,Rizvi S M A.Determinants of Gold Prices in Pakistan[M].Berlin Heidelberg:Springer,2014.
8 费一凡,陶雨芊.基于ARMA模型的黄金价格短期预测分析[J].时代金融,2018(10):236-237.
Fei Yifan,Tao Yuqian.Analysis of short-term forecast of gold price based on ARMA model[J].Times Finance,2018(10):236-237.
9 宁艳艳,方小艳,张延利.基于等维积分GM(1,1)模型的黄金价格预测[J].黄金,2016,37(7):8-10.
Ning Yanyan,Fang Xiaoyan,Zhang Yanli.Gold price prediction based on equi-dimensional integral GM(1,1) model [J].Gold,2016,37(7):8-10.
10 董杰,潘和平,姚一永,等.基于DCC-MVGARCH模型的石油、股票和黄金市场相关性实证研究[J].预测,2012,31(4):53-57.
Dong Jie,Pan Heping,Yao Yiyong,et al.Empirical study on the correlation of oil,stock and gold markets based on DCC-MVGARCH model[J].Forecasting,2012,31(4):53-57.
11 Kristjanpoller W,Minutolo M C.Gold price volatility:A forecasting approach using the Artificial Neural Network-GARCH model[J].Expert Systems with Applications,2015,42(20):7245-7251.
12 Dutta S,Ghosh D,Samanta S.Multifractal detrended cross-correlation analysis of gold price and SENSEX[J].Physica A:Statistical Mechanics and Its Applications,2014,413:195-204.
13 Khaled K,Samia M.Estimation of the parameters of the stochastic differential equations black-scholes model share price of gold[J].Journal of Mathematics and Statistics,2010,6(4):421-424.
14 Yang J H,Dou W.A new prediction method of gold price:EMD-PSO-SVM[J].Journal of Software,2014,9(1):195-202.
15 张燕平,罗斌,姚一豫,等.商空间与粒计算——结构化问题求解理论与方法[M].北京:科学出版社,2010.
Zhang Yanping,Luo Bin,Yao Yiyu,et al.Quotient Space and Granular Computing:Theory and Method of Structured Problem Solving [M].Beijing:Science Press,2010.
16 程伟,张燕平,赵姝.商空间理论框架下的SVM产量预测模型研究[J].中国农业大学学报,2009,14(5):135-139.
Cheng Wei,Zhang Yanping,Zhao Shu.Research of yield prediction model based on support vector machine within the framework of quotient space theory[J].Journal of China Agricultural University,2009,14(5):135-139.
17 王定成.支持向量机建模预测与控制[M].北京:气象出版社,2009.
Wang Dingcheng.Support Vector Machine Modeling,Forecasting and Control[M].Beijing:China Meteorological Press,2009.
18 张炳南.黄金价格、中国黄金储备与通货膨胀关系研究[J].当代经济科学,2012,34(1):75-82,126-127.
Zhang Bingnan.A study on the relationships of gold price,China gold reserve and inflation[J].Modern Economic Science,2012,34(1):75-82,126-127.
19 刘曙光,胡再勇.黄金价格的长期决定因素稳定性分析[J].世界经济研究,2008,12(2):35-41,87.
Liu Shuguang,Hu Zaiyong.An analysis of the stability of long-run determinants of the gold price[J].World Economy Study,2008,12(2):35-41,87.
20 安辉,秦伟广,谷宇.美国量化宽松货币政策对黄金价格的影响研究——基于政策宣告时点和政策实施区间的经验分析[J].国际金融研究,2016,355(11):87-96.
An Hui,Qin Weiguang,Gu Yu.Research on the impact of US quantitative easing monetary policy on gold price:Empirical study on policy announcement and policy enforcement [J].Studies of International Finance,2016,355(11):87-96.
21 刘莉.黄金价格动态预测和影响因素研究[D]山东:山东财经大学,2016.
Liu Li.Dynamic Prediction and Influence Factors Analysis on the Price of Gold[D].Shandong:Shandong University of Finance and Economics,2016.
22 王学亮.美元汇率、中国股市对黄金价格影响的实证分析[D]山东:山东大学,2014.
Wang Xueliang.Empirical Analysis of the Influence of the US Dollar Exchange Rate and the China Share Market on Gold Price[D].Shandong:Shandong University,2014.
23 王金莲.黄金价格波动与美元、石油价格波动的联动分析[D].南京:南京理工大学,2014.
Wang Jinlian.The Linkage Analysis of Fluctuations Among Gold Price,Oil Price and U.S. Dollar Index[D].Nanjing:Nanjing University of Science and Technology,2014.
24 张明.全球黄金价格的波动趋势与影响因素[J].金融评论,2013,5(4):33-47,124.
Zhang Ming.Fluctuation trend and driving factors of global gold price[J].Chinese Review of Financial Studies,2013,5(4):33-47,124.
25 王益虹.黄金价格与美元汇率走势关系的实证研究[D].杭州:浙江大学,2013.
Wang Yihong.Empirical Analysis of the Relationship Between Price and US dollar Exchange Rate[D].Hangzhou:Zhejiang University,2013.
26 付丹,梅雪,张晖.黄金价格与通货膨胀相关性的实证分析[J].黄金,2009,30(1):4-7.
Fu Dan,Mei Xue,Zhang Hui.Empirical analysis on the correlation between gold price and inflation[J].Gold,2009,30(1):4-7.
27 周华林.黄金价格影响因素的实证分析[J].重庆交通大学学报(社会科学版),2008,8(6):42-46.
Zhou Hualin.Positive analysis of influence factors to gold price[J].Journal of Chongqing Jiaotong University(Social Science Edition),2008,8(6):42-46.
[1] 王梅, 陈建宏, 杨珊. 基于等维动态马尔科夫SCGM(1,1)C模型的黄金价格预测[J]. 黄金科学技术, 2020, 28(1): 158-166.
[2] 张文平, 蔡明明, 徐超. 某含金原生矿石的工艺矿物学研究[J]. 黄金科学技术, 2019, 27(5): 770-776.
[3] 唐浪峰,盛秋月,马英强,印万忠. 非洲中南部某镍矿石工艺矿物学性质[J]. 黄金科学技术, 2019, 27(2): 285-291.
[4] 黄胤淇,肖庆飞,郭运鑫,王旭东. 江西某铜矿磨矿对比试验及应用研究[J]. 黄金科学技术, 2019, 27(2): 278-284.
[5] 毕林,崔君*,林格,谢伟. 矿井火灾最优逃生路径优化数学模型的构建与实现[J]. 黄金科学技术, 2017, 25(2): 104-109.
[6] 雷阿丽,吴彩斌,叶景胜,江领培,倪帅男,何水春. 顽石作磨矿介质下含金铜硫矿的磨矿规律研究[J]. 黄金科学技术, 2017, 25(1): 121-126.
[7] 姚福善. 大型塔式磨机在金精矿氰化细磨中的应用[J]. 黄金科学技术, 2014, 22(3): 82-85.
[8] 张树良. 近期全球黄金市场发展态势[J]. J4, 2009, 17(4): 65-69.
[9] 王忠军, 王永成, 姜维明, 胡世利, 刘金鹏. 降低金矿石回采边界品位分析与应用[J]. J4, 2007, 15(4): 54-57.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 闫杰, 覃泽礼, 谢文兵, 蔡邦永. 青海南戈滩—乌龙滩地区多金属地质特征与找矿潜力[J]. J4, 2010, 18(4): 22 -26 .
[2] 胡琴霞, 李建忠, 喻光明, 谢艳芳, 张圣潇. 白龙江成矿带金矿点初探[J]. J4, 2010, 18(3): 51 -53 .
[3] 崔廷军, 逯克思, 庄勇, 傅星. 青海省柴达木盆地南缘金成矿带特征及成矿规律浅析[J]. J4, 2010, 18(3): 63 -67 .
[4] 杨明荣, 牟长贤. 原子荧光法测定化探样品中砷和锑的不确定度评定[J]. J4, 2010, 18(3): 68 -71 .
[5] 刘胜光, 高海峰, 黄锁英. 电子手薄在山东焦家金矿地质专业中的应用[J]. J4, 2010, 18(3): 79 -82 .
[6] 黄俊,吴家富,鲁如魁 ,夏立元. 内蒙古兵图金矿成因探讨及找矿方向[J]. J4, 2010, 18(4): 1 -5 .
[7] 张渊, 张洪喜. 山东黄埠岭金矿7号脉地质特征及控矿机理研究[J]. J4, 2010, 18(4): 12 -16 .
[8] 任广智, 赵玉锁, 肖振, 卿敏, 魏峰, 缪振平. 河北峪耳崖金矿床矿体赋存规律及找矿预测[J]. J4, 2010, 18(4): 27 -32 .
[9] 李洪杰, 戚静洁, 马树江. 胶西北地区金矿床构造控矿规律[J]. J4, 2010, 18(4): 41 -46 .
[10] 路明福, 扈守全. 厚大破碎矿体回采技术的对比研究[J]. J4, 2010, 18(4): 62 -64 .