AI帮你理解科学

AI 生成解读视频

AI抽取解析论文重点内容自动生成视频


pub
生成解读视频

AI 溯源

AI解析本论文相关学术脉络


Master Reading Tree
生成 溯源树

AI 精读

AI抽取本论文的概要总结


微博一下
We wanted to propose a methodology inspired by financial mathematical models in order to extract some relevant information from Big Data that can be useful for almost any topic of interest, including finance

Structuring Big Data: How Financial Models May Help

Journal of Computer Science and Technology, (2014)

被引用6|浏览4
下载 PDF 全文
引用
微博一下

摘要

The goal of this paper is to illustrate how financial models can be used to analyze unstructured data. Indeed, with the advent of social media, researchers have access to massive amounts of new data. These new data are unstructured in the sense that they can come from multiple origins. These data are commonly called "Big Data".To analyze ...更多

代码

数据

0
简介
  • The contribution of the literature on Big Data is twofold: it addresses either the questions about the applications or the questions about the methodology.
  • With the rise of this level of connectivity comes the rise of huge amounts of personal information stored on servers.
  • Any call, any search, or any post on a website is saved
  • It is only the beginning: if the authors store personal habits today, the authors will store health information tomorrow.
  • Saving on a server 80 years of someone’s life and doing that for seven billion people represent massive quantities of information.
  • The difficulty is to implement these techniques in the real world by designing algorithms that will allow them to measure,for instance,the covariances and some forms of causation between the different variables
重点内容
  • The contribution of the literature on Big Data is twofold: it addresses either the questions about the applications or the questions about the methodology
  • The whole financial industry has been trained to read and analyze outputs based on the financial models, and it would be interesting to capitalize on these existing skills
  • We combined the two datasets in order to obtain the total value for each of the two keywords. With this dataset of unstructured data obtained through Twitter, we applied the mean-variance framework in order to interpret the perception of risk of the population
  • We wanted to propose a methodology inspired by financial mathematical models in order to extract some relevant information from Big Data that can be useful for almost any topic of interest, including finance
  • The financial models require a lot of computing power, and finance has developed with the greater access to new technologies
  • We have provided a few examples on how we could interpret the results coming out of the mathematical financial models applied to Big Data
结果
  • With this dataset of unstructured data obtained through Twitter, the authors applied the mean-variance framework in order to interpret the perception of risk of the population.
  • The authors' first modeling consisted in observing the variance and the mean return of each category of risk.
  • The public project management category appears to have a stronger volatility compared to the other categories during this period of time.
  • The components of this category include terms related to fraud, collusion and the Commission Charbonneau, which were widely spread in the media during this period.
  • The authors decided to divide the time frame into four periods, (1) from September 1st, 2012 to November 30th,2012; (2)from December 1st, 2012 to February 28th, 2013; (3) from March 1st, 2013 to May 31st, 2013; and (4) from June 1st, 2013 to August 31st, 2013
结论
  • It is often understood that the authors can extract some relevant information from Big Data to help financial decisions and to have an edge on the market.
  • This is not what the authors wanted to cover in this paper.
  • The authors do not need to take all these codes, but at the same time, why would the authors not benefit from this existing situation? the mathematical financial models are well understood and could be useful even for data whose nature is not financial
表格
  • Table1: Risk categories and their related projects or concerns [translated from French]. Source: de Marcellis-Warin and Peignier 2012
  • Table2: Descriptive statistics of each keyword
Download tables as Excel
引用论文
  • Aljohani, Naif, Saad Alahmari, and Ali Aseere. 201“An Organized Collaborative Work Using Twitter in Flood Disaster”.ACM Web Science. http://www.websci11.org/fileadmin/websci/Posters/172_paper.pdf.
    Locate open access versionFindings
  • Clarkson, Peter, Daniel Joyce, and Irene Tutticci. 2006. “Market Reaction to Takeover Rumour in Internet Discussion Sites”. SSRN Scholarly Paper ID 889785. Rochester, NY: Social Science Research Network. http://papers.ssrn.com/abstract=889785.
    Findings
  • Crampton, Jeremy W., Mark Graham, Atius Poorthius, Taylor Shelton, Monica Stephens, Matthew W. Wilson, and Matthew Zook. 201“Beyond the Geotag Situating Big Data and Leveraging the Potential of the Geoweb”. Accessed April 7.
    Google ScholarFindings
  • http://www.academia.edu/2986482/Beyond_the_Geotag_Situating_big_data_and_leveragin g_the_potential_of_the_geoweb.
    Findings
  • Culotta, Aron. 2010. “Towards detecting influenza epidemics by analyzing Twitter messages”. In Proceedings of the First Workshop on Social Media Analytics, pp.115–122. SOMA ’10. New York, NY, USA: ACM. doi:10.1145/1964858.1964874. http://doi.acm.org/10.1145/1964858.1964874.
    Locate open access versionFindings
  • Diebold, Francis X. 2012. “A Personal Perspective on the Origin(s) and Development of ‘Big Data’: The Phenomenon, the Term, and the Discipline, Second Version”. PIER Working Paper Archive 13-003. Penn Institute for Economic Research, Department of Economics, University of Pennsylvania. http://ideas.repec.org/p/pen/papers/13003.html.
    Locate open access versionFindings
  • Laney, Douglas. 2001. “3D Data Management: Controlling Data Volume, Velocity, and Variety”. META Group. http://blogs.gartner.com/douglaney/files/2012/01/ad949-3D-Data-Management-Controlling-Data-VolumeVelocity-and-Variety.pdf.
    Locate open access versionFindings
  • Lintner, John. 1965. “The Valuation of Risk Assets and the Selection of Risky Investments in Stock Portfolios and Capital Budgets”.The Review of Economics and Statistics, Vol. 47 (1) (February), pp. 13–37. doi:10.2307/1924119.
    Locate open access versionFindings
  • Marcellis-Warin, Nathalie de, and Ingrid Peignier. 2012. “Perception des risques au Québec – Baromètre CIRANO 2012”. CIRANO Monographs. CIRANO. http://ideas.repec.org/b/cir/cirmon/2012mo-02.html.
    Locate open access versionFindings
  • Markowitz, Harry. 1952. “Portfolio Selection”.The Journal of Finance, Vol. 7 (1) (March 1), pp. 77–91. doi:10.1111/j.1540-6261.1952.tb01525.x.
    Locate open access versionFindings
  • McKelvey, Karissa, and Filippo Menczer. 2013. “Design and Prototyping of a Social Media Observatory”. In Proceedings of the 22nd International Conference on World Wide Web Companion, pp. 1351–1358. WWW ’13 Companion. Republic and Canton of Geneva, Switzerland: International World Wide Web Conferences Steering Committee. http://dl.acm.org/citation.cfm?id=2487788.2488174.
    Locate open access versionFindings
  • Mossin, Jan. 1966. “Equilibrium in a Capital Asset Market”.Econometrica, Vol. 34 (4) (October), pp. 768–783. doi:10.2307/1910098.
    Locate open access versionFindings
  • Sharpe, William F. 1963. “A Simplified Model for Portfolio Analysis”.Management Science, Vol. 9 (2) (January 1), pp. 277–293.
    Google ScholarLocate open access versionFindings
  • Sprenger, Timm, and Isabell Welpe. 2010. “Tweets and Trades: The Information Content of Stock Microblogs”. SSRN Scholarly Paper ID 1702854. Rochester, NY: Social
    Google ScholarFindings
  • Science Research Network. http://papers.ssrn.com/abstract=1702854. Stover Tillinghast, Diana, Dannah Sanchez, Matthew Gerring, and Sarah Hassan.2012.
    Findings
作者
william sanger
william sanger
您的评分 :
0

 

标签
评论
数据免责声明
页面数据均来自互联网公开来源、合作出版商和通过AI技术自动分析结果,我们不对页面数据的有效性、准确性、正确性、可靠性、完整性和及时性做出任何承诺和保证。若有疑问,可以通过电子邮件方式联系我们:report@aminer.cn
小科