基于支持向量机的金融时序数据预测算法分析-analysis of financial timing data prediction algorithm based on support vector machine.docxVIP

下载本文档

7
0
约4.36万字
约 49页
2018-08-14 发布于上海
举报
版权申诉

基于支持向量机的金融时序数据预测算法分析-analysis of financial timing data prediction algorithm based on support vector machine.docx

1、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。。
2、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
4、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
5、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
6、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
7、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

基于支持向量机的金融时序数据预测算法分析-analysis of financial timing data prediction algorithm based on support vector machine

Resarch on the data of financial time series prediction algorithm based Supporting Vector MachineAB STRACTO n the predictio n of financ ia l t ime series data, in order to minimize r isk structure, Vapnik proposed SVM in 1995. Due to the structura l r isk minimizat io n princ ip le of support vector machine both emp ir ical r isk and confide nce inter va l of the two aspects, rather than minimizing seek only t he emp ir ica l r isk, so is proved to have better performa nce than ne ura l network model. A nother advanta ge of support vector machine is that it in the process of training model, d imens ion ca lculat io n comple xit y does not depend on the input space. At first, support vector machine is wide ly used in pattern recognit ion, machine learning and other fie lds, has been extended to nonlinear regress ion proble ms.In t he fie ld of financ ia l t ime series predictio n, there are a large number of stud ies show that, the relat ions hip between input var iables and outp ut var iab les are changed over t ime, and for t he predict ion problem, recent data more long- term data provide more infor mat ion, so the natural idea is higher we ight give n to recent infor mat io n. This paper selects the stock price index as the fina nc ia l t ime series data out predictio n and ana lys is.The stock is closely re lated to the lives of t he masses as well as socia l a nd economic developme nt, so stock predict ion has ver y important practical s ignifica nce in socia l life.The stock predict ion syste m using two algor ithms to achieve the forecast on thestock contour. The first algor ithm is a support vector machine regressio n predict ion algorit hm. First, build a model according to the characterist ic va lue o f the stock data, and then use the model to forecast stock contour, fina lly, characteristic va lue of t he stock, and only t ime as an independent variab le. The n granulate the time informat io