摘要
文章以我国六个碳金融试点市场每个月份的风险状态为研究样本,构建基于支持向量机(SVM)的碳金融风险预警模型。利用网格搜索法和径向基核函数构建的SVM模型对碳金融风险的预警准确率高达91.860 5%,对我国六个碳金融试点市场进行预警后发现,北京、上海试点市场风险较大,天津、深圳市场居中,广东和湖北市场相对健康。最后根据研究结论提出相关建议。
This paper,by taking the monthly risk state of six carbon financial pilot markets in China as the research samples,constructs a carbon financial risk early warning model based on SVM. The SVM model constructed by the grid search method and the radial basis function predicts the carbon financial risk with an accuracy of 91.8605%. After carrying out the early warning of six carbon financial pilot markets,the paper finds that Beijing and Shanghai markets are more risky,followed by Tianjin and Shenzhen markets,Guangdong and Hubei markets are relatively safe. Finally,the paper proposes relevant suggestions according to the study conclusions.
引文
[1]LARSON D F,PARKS P. Risks,Lessons Learned,and Secondary Markets for Greenhouse Gas Reductions[R]. Policy Research Working Paper,2009.
[2]DUTSCHKE M,SCHLAMADINGER B,WONG J L P,et al.Value and Risks of Expiring Carbon Credits from CDM Afforestation and Reforestation[J]. Ssrn Electronic Journal,2004(5):20-33.
[3]Carbon Finance at the World Bank. State and Trends of the Carbon Market 2011[R]. Washington D C:World Bank Institute,2011.
[4]KARL MARTIN E,CHRISTIAN H,JOACHIM S,et al. The role of auctions and forward markets in the EU ETS:counter balancing the cost inefficiencies of combining generous allocation with a ban on banking[J]. Climate Policy,2005,5(1):31-46.
[5]MOSLENER U,SCHEL A. Assessing emission allocation in European:an interactive simulation approach[R]. ZEWCenter for European Economic Research Discussion Paper,2004.
[6]STRANLUND J K. The regulatory choice of noncompliance in emissions trading Programs[J]. Environmental and Resource Economics,2007,38(1):99-117.
[7]DASKALAKIS G,PSYCHOYIOS D,MARKELLOS R N.Modeling CO2 emission allowance prices and derivatives:Evidence from the European trading scheme[J]. Journal of Banking&Finance,2009(1):1-35.
[8]MARKELLOS N. Are the European Carbon markets efficient[J]. Review of Futures Markets,2008(2):103-128.
[9]史晓琳.构建我国商业银行碳金融内部风险管理长效机制[J].金融论坛,2010(Z1):21-27.
[10]刘志成.我国发展碳金融面临的风险和对策[J].武汉金融,2012(6):31-33.
[11]王定祥,琚丽娟.碳金融理论研究评述与展望[J].西部论坛,2013(1):70-79.
[12]杜莉,王利,张云.碳金融交易风险:度量与防控[J].经济管理,2014(4):106-115.
[13]周纪昌.构建我国商业银行碳金融风险管理机制[J].金融理论与实践,2012(10):63-66.
[14]孙立行.开放条件下中国金融风险预警指标体系研究[J].世界经济研究,2012(12):30-36.
[15]许传华,徐慧玲,杨雪莱.我国金融风险预警模型的建立与实证研究[J].经济问题,2012(2):83-86.
[16]胡海青,张琅,张道宏.基于支持向量机的供应链金融信用风险评估研究[J].软科学,2011,25(5):26-30.
[17]刘道文,樊明智.基于支持向量机股票价格指数建模及预测[J].统计与决策,2013(2):76-78.
[18]赛英,张凤廷,张涛.基于支持向量机的中国股指期货回归预测研究[J].中国管理科学,2013,21(3):35-39.
[19]隋学深,乔鹏,丁保利.基于支持向量机的贷款风险等级分类真实性审计研究[J].审计研究,2014(3):21-25.
[20]顾建华.中国低碳经济增长效率的空间格局与演变趋势[J].西部论坛,2017(2):39-428.
[21]胡冰.加快推进我国产业结构低碳转型的产业经验与路径选择[J].理论探讨,2017(1):78-82.
(1)“碳泄漏”是指企业将其生产或投资转移至那些排放成本较低的地区或国家的现象。碳泄露源自碳价波动,碳泄露不仅在一定程度上增加了碳排放,也增大了碳市场的风险。
(2)“碳逆转”是指碳吸收逆转为碳排放,其中“碳吸收”是指通过技术手段将游离的二氧化碳等温室气体固化,并储存起来,即设法减少大气中的碳存量。
(3)我国七个碳试点市场中重庆市场不活跃,缺乏连续的碳排放权成交数据,故本文不考虑重庆市场。
(4)由于篇幅限制,因子载荷矩阵不再列出。
