16
Two Decades of Big Data in Finance : Systematic Literature Review and Future Research Agenda

Nufazil Altaf

School of Business Studies, Central University of Kashmir, Kashmir, India

16.1 Introduction

[1] defined “Big data analytics” as a combination of two words “big data” and “analytics.” While big data refers to the voluminously large datasets, analytics refers to using these datasets to reveal patterns, trends, and associations that can be applied as a solution to various complex problems [2]. The past decade witnessed the growth in the application of big data analytics to the area of finance, particularly to the stock market finance. Finance practitioners viewed big data analytics as a powerful tool to improve the risk analysis process, enhance the fraud detection and prevention, and change the trade and investment paradigm from “of no moment” to “real‐time” settlement [3]. Not surprising, many scholarly evidence also emerged that elaborated upon the application of big data analytics to the finance industry [3–8]. Specifically, these researchers viewed the application of big data to various finance businesses like crowd‐funding, crypto‐currency, wealth management, SME finance, asset–liability management, trading platforms, payment and settlement system, and so on. These businesses generate an enormous amount of data and therefore the management of such data is an important factor in these businesses (Hasan et al. [3]). In line with this, big data has received overwhelming attention in the finance industry, where managers know that bits of information is an important part of the success of the enterprise.

Although the practitioners of finance believe that role of big data in the Internet of Things (IoT) is more about processing and gathering information about financial transactions that may be ideal for decision‐making. Yet, many financial analysts believe that the application of the IoT in the finance industry as a technological suite has a transformative effect on every dimension of financial and economic activity across the globe. The potential benefits of IoT in finance are seen in providing more comprehensive real‐time data for decision‐making. Additionally, innovative financial products like auto insurance telematics and customized banking services are examples of new products that became possible only because of IoT application to the finance industry. Therefore, the use of IoT in finance goes far beyond mere data communication and analysis and has been seen as a strategic gamification tool and incentivizes lower risk in the finance industry even if it is in the early stages of its development.

Beveled by the response of big data analytics as an information processing tool, the first illustration of the application of big data to finance was presented by [9]. In this study, the researcher investigated the textual content of a column in the Wall Street Journal “Abreast of the Market” as a prognosticator of market returns. Additionally, [9] also applied text analysis to predict companies’ fundamentals. One more study on textual data was conducted by [10], who asserted that firms with a detailed description of products end up in a merger. Some studies, like [11], used Bayes algorithms for performing linguistic analysis. They suggested that disagreement in messages is associated with increased volatility. However, [12] criticized Bayes approaches and suggested that these approaches do not work in the finance industry. They proposed new positive and negative words that provided signals of volatility, trading volume, and so on, and were highly applicable to finance.

Some researchers like [13, 14] suggested that intraday data such as the flow of order types predict returns on a daily horizon. In a similar vein, [15] indicated that data from retail investor trades contain valuable information and they predict the returns positively with no reversals for a month. In follow‐up research, [16] suggested that short sales of retail investors also predict stock returns but negatively. Using the ranking of stocks, [17] suggested that the higher the ranking of the stock, the lower will be the returns. Further, [18] assert that technical analysis tools are strong predictors of future stock returns, [19] suggest that interest in the company is conveyed through internet searches and search engines record these searches and sometimes such interest predicts returns.

Further, [20] suggested that product quality rating by customers of Amazon is one of the potential factors that affect returns, [10] assert that the proportion of negative words (opinions) posted by the investors on the investment blog acts as a significant determinant of lower returns on the stock. Additionally, [21] find that the volume of its posts predicts the company’s abnormal returns.

The literature’s critical review suggests that the studies on big data analytics in finance are mostly related to financial markets, internet finance, and financial services. Thereby keeping in view the increased acceptance of big data in the finance industry, this study attempts to contribute to the literature by conducting a systematic literature review (SLR) in an endeavor to collect the views of scholars, academicians, and industry practitioners related to big data and finance. This study will help gain deeper insights into the understanding of research conducted on big data in the area of finance and thereby discuss the findings of these studies as an implication to the finance industry. Additionally, the study attempts to provide directions for future research as a challenge to be faced by academicians and researchers.

The rest of the paper is organized as follows: Section 16.2 describes the methodology adopted for the study. Section 16.3 describes the article identification and selection process. Section 16.4 deliberates upon the description and classification of literature. Section 16.5 provides the content and citation analysis of articles and Section 16.6 reports the findings and research gaps.

16.2 Methodology

Following [22, 23], we conduct a SLR in this paper. SLR is recognized as a comprehensive methodology for conducting literature reviews. Additionally, SLR describes the procedures, processes by which all relevant material related to a particular phenomenon will be collected [24]. Accordingly, the adapted review process for identifying the issues and future avenues in big data for finance research is categorized into four phases, as shown in Figure 16.1.

16.3 Article Identification and Selection

The search of the published journal articles for big data in finance was made in the major academic databases like Scopus, Web of Science, and EBSCO. It must be noted that these three academic databases were chosen because they hold the academic might. The search began by a keyword (Big data) search that resulted in a huge amount of literature. The article that had the keyword “Big data” in the title, keywords, or abstract was initially selected. Following the keyword search, delimiting boundaries were setup for removing the unwanted articles. The delimiting boundaries’ setup is as follows:

Schematic illustration of the procedure for systematic literature review.

Figure 16.1 Procedure for systematic literature review.

Source: From Singh and Kumar [22].

Table 16.1 Article identification and selection.

Database Time‐horizon Total number of articles Total number of selected articles
Scopus 2000–2019 85 46
Web of science 2000–2019 57 32
EBSCO 2000–2019 48 27
Total 190 105
  • Papers for which full‐text was available.
  • Papers were collected from 2000 to 2019.
  • Papers disseminating links of big data for finance were only considered.

After the application of delimiting boundaries, the total number of articles available for reading was 190. However, after reading the articles, it was found that some articles were indexed in more than one database. Therefore, to remove duplicity, 85 articles were removed, leaving us with 105 articles as the final sample. The article availability and selection are given in Table 16.1. Perusing Table 16.1, the total number of articles found initially in the Scopus database was equal to 85, in Web of Science 57, and EBSCO 48. However, after removing duplicity or more than one indexing, the article that was solely indexed in Scopus was 46, in Web of Science 32, and EBSCO 27, making the total sample equal to 105 unique articles.

16.4 Description and Classification of Literature

The selected 105 published journal articles are further analyzed with regard to the research method employed, publications (year wise), and journal of publication. This exercise helps to identify the trends prevalent in big data for finance literature.

16.4.1 Research Method Employed

The published articles are broadly classified into three categories based on the research method employed; these include empirical, conceptual, and survey. The frequencies and percentage of articles within each group of research methods are given in Table 16.2. Perusing the table, it can be found that 75.23% (79) of articles employ empirical methodology and such methodology has remained most popular among the scholars working on big data in finance. The conceptual methodology is the second most popular among the researchers, while a survey methodology has not received much interest in the last two decades of research in big data for finance.

16.4.2 Articles Published Year Wise

Figure 16.2 presents the number of articles published from 2000 to 2019 across years. The visual presentation of the graph helps us to divide the time frame into three phases, the first phase (2000–2009), the second phase (2010–2013), and the third phase (2014–2019). The first phase can be regarded as a low growth phase because the number of articles published during these years amounts to be very less. It may be due to the low acceptance of big data in the area of finance. The second phase can be regarded as medium growth phase, during this phase the number of articles being published on big data for finance started growing, and lastly the third phase can be regarded as high growth phase, during this phase number of articles being published every year entered two digits, in fact, the maximum number of articles (15) were published in 2018, during this phase. The growth in the literature from the second phase may be due to the advent of the global financial crisis, where scholars and practitioners reacted by developing innovative methods to streamline crisis, big data is one such example.

Table 16.2 Articles according to research method employed.

Research method No of articles Percentage of articles
Empirical 79 75.23
Conceptual 21 20
Survey 5 4.77
Bar chart depicts the articles published year wise.

Figure 16.2 Articles published year wise.

16.4.3 Journal of Publication

The main aim of analysis by the journal of publication is to identify the journals that have taken the lead in disseminating information on big data in finance. Such information is presented in Table 16.3. It must be noted that from the long list of journals we have presented, only the journals that have published at least two papers on the topic during 2000–20191. Among the long list of journals International Journal of Information Management has published a maximum of seven articles followed by the Journal of Econometrics and Journal of Business Research with six articles, respectively. The Journal of Big Data, Physica A: Statistical Mechanics and its Applications and Decision Support System have published five articles from 2000 to 2019. Further, a detailed list is presented in Table 16.3.

16.5 Content and Citation Analysis of Articles

In this section, we first take up the citation analysis followed by content analysis.

16.5.1 Citation Analysis

Citation is referred to as the reference of the work of one author made by another author. Citation analysis aims to identify the most influential and popular work among the researchers. The results of citation analysis are presented in Table 16.4. It must be noted that to save space, we have only presented the author(s) that have been cited at least 20 times. Additionally, it must be noted that we used citation information provided by Google Scholar for citation analysis. Further, it must be noted that among the 105 articles, 23 articles were not cited; however, these articles were published recently during 2018 and 2019. This may be the possible reason that these articles were not cited at all. Additionally, 105 articles have a total citation count of 2205, implying that the average citation per article was 21. The most influential and cited work is [25] with 395 citations, followed by [26] with 344 citations and [27] with 234 citations. These articles have received tremendous response and it may be because these articles are among the early works on big data in finance. The rest of the author(s) presented in Table 16.4 have citations in two digits.

Table 16.3 Journal of publication.

S. No. Journal name Publisher No. of articles published
1. International Journal of Information Management Elsevier 7
2. Journal of Econometrics Elsevier 6
3. Journal of Business Research Elsevier 6
4. Journal of Big Data Springer 5
5. Physica A: Statistical Mechanics and its Applications Elsevier 5
6. Decision Support System Elsevier 5
7. Emerging Markets Finance and Trade Taylor & Francis 4
8. MIT Sloan Management Review MIT 4
9. Intelligent Systems in Accounting, Finance and Management Wiley 4
10. Journal of Behavioral and Experimental Finance Elsevier 3
11. Journal of Risk and Financial Management MDPI 3
12. Electronic Commerce Research Springer 3
13. The Journal of Corporate Accounting & Finance Wiley 3
14. Journal of Monetary Economics Elsevier 2
15. The Journal of Finance and Data science Elsevier 2
16. Australian Accounting Review Wiley 2
17. International Journal of Electronic Commerce Taylor & Francis 2
18. Wireless Personal Communications Springer 2

16.5.2 Content Analysis

Through content analysis of the selected articles, we provide in‐depth details where the research on big data in finance has been concentrated. It is worth noting that most of the research has been focused on big data for financial markets, internet finance, financial services, and other issues.

Table 16.4 Citation analysis.

S. No. Author(s) Citation
1. Drake et al. [25] 395
2. Einav and Levin [26] 344
3. Dimpfl and Jank [27] 234
4. Kshetri [28] 78
5. Seddon and Currie [29] 59
6. Begenau et al. [4] 49
7. Chen et al. [30] 39
8. Campbell et al. [31] 37
9. Jin et al. [32] 36
10. Choi and Lambert [33] 28
11. Cerchiello and Giudici [34] 24
12. Côrte‐Real et al. [35] 22
13. Fanning and Grant [36] 21
14. Pejić Bach et al. [37] 20
15. Pérez‐Martín et al. [38] 20
16. Blackburn et al. [39] 20
17. Tian et al. [40] 20
18. Xie et al. [41] 20

16.5.2.1 Big Data in Financial Markets

It is regarded that big data stimulate the financial markets by helping in returns prediction, valuations, forecasting volatility, algorithmic trading, and so on. In fact, it has been asserted that the efficiency of the financial markets is attributed to the amount of information it generates and its diffusion process. In fact, technological innovations that generate information are regarded to positively impact financial markets [3]. It is for this reason that the market overreacts to extremely negative news [42]. Additionally, opinions, ratings, and posts on social media also have an impact on the financial markets. For instance, [21] found that opinions and ratings predict company returns. Additionally, [17] show that stocks’ aggregate rankings are negatively associated with future returns. Therefore, the amount of information generated acts as an influential force affecting the global financial markets.

More recently, [42] found that messages sent to the NASDAQ exchange for the S&P 500 were essential to establish a true market price. The increased electronic trading has generated interest among the fund managers for the use of big data [43], interpret the pricing screens [41], interpret the complex market data by using visualization software [15], and the use of technologies to facilitate electronic trading in the global coordination [44].

Further, given a large number of anomalies present in forecasting returns, big data presents promising upshots in forecasting stock returns even when the variables and stock returns change over time. Therefore, in forecasting future stock returns, big data can reduce uncertainty in investment outcomes. In fact, more data processing reduces the uncertainty that ultimately reduces the risk and the overall cost of capital [4].

16.5.2.2 Big Data in Internet Finance

Internet finance is regarded as an intersection of big data, cloud computing, social networking, and information technology over the Internet [45], making internet finance a new phenomenon in finance when compared to traditional finance. Internet finance includes electronic cash transfers, electronic payment and settlements, crowd‐funding, peer‐to‐peer lending, and so on. However, these financial interactions take place over the Internet and thereby, internet finance is regarded as the integration of modern finance and technology. With the advent of internet finance, modern banking, online transactions, and banking applications produce a million pieces of data every day and the management of this data is important [3].

[41] recently explored the fundamentals of internet finance in abreast of explaining the relationship between information technology, e‐commerce, and finance. They used factors like service variety, information protection, data volume, and predictive correctness as factors to explain this relationship. Further, it is contended that big data improve the risk management practices, alleviate information asymmetry problems, predict credit risk, and detect fraud [46, 47]. In fact, data mining technology is regarded as the chief factor in risk management and fraud detection and prevention [32, 37, 48].

Further, big data by way of information sharing has resulted in the formation of a transparent and competitive market where pricing processes are fair and smooth. This helps to further reduce the parties’ financial disputes and improve dispute resolution [45]. Additionally, by way of data access, big data has impacted internet credit service companies. These companies are now able to access more borrowers, which was not possible with traditional models. Overall, big data has significantly uplifted financial institutions toward efficiency and approaching new consumers.

16.5.2.3 Big Data in Financial Services

The current landscape of the financial service industries’ business model is changing rapidly with the advent of big data. In fact, many financial service firms are working toward developing novel business models that would consider the application of big data [3]. Further, it is asserted that such business models must incorporate big data application into risk control, creating finance sentiment indexes and financial market analysis for these institutions. As every financial services company receives and generates data in billions of pieces every day, their management is important for the overall risk management and profit maximization [49]. In line with this, [49] described four features of big data, volume (data of large scale), variety (data in different formats), velocity (data of different frequencies), and veracity (data is uncertain). These characteristics pose a challenge to the management of financial services firms for the application of big data and finding novel business models in handling big data.

Further, [33] assert that big data is increasingly important for risk analysis in financial service institutions. They suggest that big data enhances risk management by improving the quality of models and applying behavior scorecards. Big data also helps in interpreting the risk analysis information faster compared to traditional systems [50]. Additionally, [34] specified the risk modeling process that focuses on the interrelationships between financial institutions.

Further, [38] suggested that big data analytics measure credit risk in banking firms. They also suggest that the management of databases is important for automatic evaluation of credit status within a reasonable period. In fact, nowadays, big data techniques are applied in banking firms to segment risk groups and comply with legal and regulatory requirements. Overall, it is suggested that financial institutions must benefit from improved system bought up by big data.

16.5.2.4 Big Data and Other Financial Issues

Big data has also been applied to the management of personal finance [3]. Further, [4] asserts that big data in financial markets has enabled large firms to grow faster because big data helped large firms lower the cost of capital in a greater proportion compared to small ones. The significant relationship between information and the cost of capital is also supported by [51]. Further, [52] embeds big data into corporate finance and investment decision models. Additionally, [53] suggest a significant relationship exists between Internet message board activity and abnormal stock returns and trading volume. Moreover, [54] thrust upon the usefulness of big data analytics in financial statement audits.

16.6 Reporting of Findings and Research Gaps

This section is dedicated to the presentation of overall findings from the articles reviewed and identification of gaps thereof. It is worth mentioning that care has been taken to deliberate upon the major findings from the literature that are instrumental upon research gaps’ identification.

16.6.1 Findings from the Literature Review

The critical review of the literature identifies the followings findings:

16.6.1.1 Lack of Symmetry

The studies conducted so far on big data in finance lack the symmetric theory development. In fact, the studies conducted so far deliberate upon different operational aspects of big data in finance, for instance, [4] considers big data in finance and growth of firms; [27] studies internet search queries as a predictor of stock market volatility; [8] intends to explain the value of big data for internet credit service companies; [26] deliberates upon the working of economics in the age of big data; [25] pondered upon google searches around earning announcements; [54] explained the usefulness of big data analytics in financial statement audits.

The lack of symmetry in the literature can be attributed firstly to the newness of big data in finance, secondly to the relatively smaller amount of big data in finance research. Given this finding in the literature, a future research opportunity emerges concerning the development of symmetric theory for big data in finance.

16.6.1.2 Dominance of Research on Financial Markets, Internet Finance, and Financial Services

Another key finding from the literature emerges with regard to the dominance of the research of big data in finance in the above‐mentioned areas. Studies like [42, 43, 55] extensively researched on big data in financial markets, studies like [32, 37, 41] explored big data in internet finance, and some studies worked on big data in financial services, for instance [39, 42, 43].

The dominance of literature of big data in finance in these specific areas maybe because most of the journals publishing articles on big data in finance call papers in these specific areas. Additionally, these areas of finance have the direct application of the Internet or are internet‐based industries, hence big data as an application in finance would naturally grow in such areas. Given this finding, future research can be conducted by extensively exploring other areas of finance like corporate finance, accounting, agriculture finance, and so on.

16.6.1.3 Dominance of Empirical Research

Based on the results mentioned in Table 16.2, the majority of the research articles were focused on conducting empirical research. In fact, 75% of the articles were such. These results should not be surprising as finance research is dominated by empirical setup. The other reason for the lack of qualitative and survey enquiry is that not many journals publish such research, at least not in the finance area. This finding puts thrust on conducting future research as a mixed enquiry or qualitative and survey‐based research.

16.6.2 Directions for Future Research

Apart from the above‐mentioned areas, future research can also be conducted by addressing technical problems with regard to data management. Additionally, there are a large number of datasets available, such as Eagle Alpha provides the dataset on customer receipts that can be used to forecast revenue, Twitter sentiment data on companies, and an attractive piece of the dataset is provided by iSentient. These datasets have not entered the academic space, thereby results gained after their analysis would be quite useful.

As mentioned earlier, big data in finance has been focused on a few specific areas; future research can be carried out by exploring its impact on a variety of organizational characteristics. Machine learning is also being considered as a promising area for academic work. Machine learning, coupled with big data, can do wonders; it can improve forecasts, risk management, prediction, and so on. Such an area can be a possible interest for academicians. In fact, software packages like R and Python have simplified these procedures and applications. Therefore, this area might find its space in the academic arena of finance.

References

  1. 1 Russom, P. (2011). Big data analytics. TDWI Best Practices Report, Fourth Quarter 19 (4): 1–34.
  2. 2 Suthaharan, S. (2016). Machine learning models and algorithms for big data classification. Integrated Series in Information Systems 36: 1–12.
  3. 3 Hasan, M.M., Popp, J., and Oláh, J. (2020). Current landscape and influence of big data on finance. Journal of Big Data 7 (1): 1–17.
  4. 4 Begenau, J., Farboodi, M., and Veldkamp, L. (2018). Big data in finance and the growth of large firms. Journal of Monetary Economics 97: 71–87.
  5. 5 Zetsche, D.A., Buckley, R.P., Arner, D.W., and Barberis, J.N. (2017). From fintech to techfin: the regulatory challenges of data‐driven finance. NYU Journal of Law and Business 14: 393.
  6. 6 Fang, B. and Zhang, P. (2016). Big data in finance. In: Big Data Concepts, Theories, and Applications, 391–412. Cham: Springer.
  7. 7 Woodard, J. (2016). Big data and ag‐analytics. Agricultural Finance Review. 76 (1): 15–26.
  8. 8 Zhang, S., Xiong, W., Ni, W., and Li, X. (2015). Value of big data to finance: observations on an internet credit Service Company in China. Financial Innovation 1 (1): 17.
  9. 9 Tetlock, P.C. (2007). Giving content to investor sentiment: the role of media in the stock market. The Journal of Finance 62 (3): 1139–1168.
  10. 10 Hoberg, G. and Phillips, G. (2010). Product market synergies and competition in mergers and acquisitions: a text‐based analysis. The Review of Financial Studies 23 (10): 3773–3811.
  11. 11 Antweiler, W. and Frank, M.Z. (2004). Is all that talk just noise? The information content of internet stock message boards. The Journal of Finance 59 (3): 1259–1294.
  12. 12 Loughran, T. and McDonald, B. (2011). When is a liability not a liability? Textual analysis, dictionaries, and 10‐Ks. The Journal of Finance 66 (1): 35–65.
  13. 13 Heston, S.L., Korajczyk, R.A., and Sadka, R. (2010). Intraday patterns in the cross‐section of stock returns. The Journal of Finance 65 (4): 1369–1407.
  14. 14 Chordia, T. and Subrahmanyam, A. (2004). Order imbalance and individual stock returns: theory and evidence. Journal of Financial Economics 72 (3): 485–518.
  15. 15 Kelley, E.K. and Tetlock, P.C. (2013). How wise are crowds? Insights from retail orders and stock returns. The Journal of Finance 68 (3): 1229–1265.
  16. 16 Kelley, E.K. and Tetlock, P.C. (2016). Retail short selling and stock prices. The Review of Financial Studies 30 (3): 801–834.
  17. 17 Da, Z., Huang, X., and Jin, L.J. (2019). Extrapolative beliefs in the cross‐section: What can we learn from the crowds? Journal of Financial Economics Available at SSRN 3144849.
  18. 18 Neely, C.J., Rapach, D.E., Tu, J., and Zhou, G. (2014). Forecasting the equity risk premium: the role of technical indicators. Management Science 60 (7): 1772–1791.
  19. 19 Da, Z., Engelberg, J., and Gao, P. (2011). In search of attention. The Journal of Finance 66 (5): 1461–1499.
  20. 20 Huang, J. (2018). The customer knows best: the investment value of consumer opinions. Journal of Financial Economics 128 (1): 164–182.
  21. 21 Tirunillai, S. and Tellis, G.J. (2012). Does chatter really matter? Dynamics of user‐generated content and stock performance. Marketing Science 31 (2): 198–215.
  22. 22 Singh, H.P. and Kumar, S. (2014). Working capital management: a literature review and research agenda. Qualitative Research in Financial Markets 6 (2): 173–197.
  23. 23 Tranfield, D., Denyer, D., and Smart, P. (2003). Towards a methodology for developing evidence‐informed management knowledge by means of systematic review. British Journal of Management 14 (3): 207–222.
  24. 24 Fink, A. (2019). Conducting Research Literature Reviews: From the Internet to Paper. Sage publications.
  25. 25 Drake, M.S., Roulstone, D.T., and Thornock, J.R. (2012). Investor information demand: evidence from Google searches around earnings announcements. Journal of Accounting Research 50 (4): 1001–1040.
  26. 26 Einav, L. and Levin, J. (2014). The data revolution and economic analysis. Innovation Policy and the Economy 14 (1): 1–24.
  27. 27 Dimpfl, T. and Jank, S. (2016). Can internet search queries help to predict stock market volatility? European Financial Management 22 (2): 171–192.
  28. 28 Kshetri, N. (2016). Big data’s role in expanding access to financial services in China. International journal of information management 36 (3): 297–308.
  29. 29 Seddon, J.J. and Currie, W.L. (2017). A model for unpacking big data analytics in high‐frequency trading. Journal of Business Research 70: 300–307.
  30. 30 Chen, Y., Chen, H., Gorkhali, A. et al. (2015). Big data analytics and big data science: a survey. Journal of Management Analytics 3 (1): 1–42.
  31. 31 Campbell‐Verduyn, M., Goguen, M., and Porter, T. (2017). Big data and algorithmic governance: the case of financial practices. New Political Economy 22 (2): 219–236.
  32. 32 Jin, X., Shen, D., and Zhang, W. (2016). Has microblogging changed stock market behavior? Evidence from China. Physica A: Statistical Mechanics and its Applications 452: 151–156.
  33. 33 Choi, T.M. and Lambert, J.H. (2017). Advances in risk analysis with big data. Risk Analysis 37 (8): 1435–1442.
  34. 34 Cerchiello, P. and Giudici, P. (2016). Big data analysis for financial risk management. Journal of Big Data 3 (1): 18.
  35. 35 Côrte‐Real, N., Ruivo, P., Oliveira, T., and Popovič, A. (2019). Unlocking the drivers of big data analytics value in firms. Journal of Business Research 97: 160–173.
  36. 36 Fanning, K. and Grant, R. (2013). Big data: implications for financial managers. Journal of Corporate Accounting & Finance 24 (5): 23–30.
  37. 37 Pejić Bach, M., Krstić, Ž., Seljan, S., and Turulja, L. (2019). Text mining for big data analysis in financial sector: a literature review. Sustainability 11 (5): 1277.
  38. 38 Pérez‐Martín, A., Pérez‐Torregrosa, A., and Vaca, M. (2018). Big Data techniques to measure credit banking risk in home equity loans. Journal of Business Research 89: 448–454.
  39. 39 Blackburn, M., Alexander, J., Legan, J.D., and Klabjan, D. (2017). Big data and the future of R&D management: the rise of big data and big data analytics will have significant implications for R&D and innovation management in the next decade. Research‐Technology Management 60 (5): 43–51.
  40. 40 Tian, X., Han, R., Wang, L. et al. (2015). Latency critical big data computing in finance. The Journal of Finance and Data Science 1 (1): 33–41.
  41. 41 Xie, P., Zou, C., and Liu, H. (2016). The fundamentals of internet finance and its policy implications in China. China Economic Journal 9 (3): 240–252.
  42. 42 Blocher, J., Cooper, R., Seddon, J., & Van Vliet, B. (2018). Phantom liquidity and high‐frequency quoting. Journal of Trading, Vol. 11, No. 3, 6–15.
  43. 43 Preda, A. (2007a). The sociological approach to financial markets. Journal of Economic Surveys 21 (3): 506–533.
  44. 44 Zaloom, C. (2003). Ambiguous numbers: trading technologies and interpretation in financial markets. American Ethnologist 30 (2): 258–272.
  45. 45 Yang, D., Chen, P., Shi, F., and Wen, C. (2018). Internet finance: its uncertain legal foundations and the role of big data in its development. Emerging Markets Finance and Trade 54 (4): 721–732.
  46. 46 Glancy, F.H. and Yadav, S.B. (2011). A computational model for financial reporting fraud detection. Decision Support Systems 50 (3): 595–601.
  47. 47 Ngai, E.W., Hu, Y., Wong, Y.H. et al. (2011). The application of data mining techniques in financial fraud detection: a classification framework and an academic review of literature. Decision Support Systems 50 (3): 559–569.
  48. 48 Hajizadeh, E., Ardakani, H.D., and Shahrabi, J. (2010). Application of data mining techniques in stock markets: a survey. Journal of Economics and International Finance 2 (7): 109.
  49. 49 Sun, Y., Shi, Y., and Zhang, Z. (2019). Finance Big Data: management, analysis, and applications. International Journal of Electronic Commerce 23: 1.
  50. 50 Hennessy, C.A. and Whited, T.M. (2007). How costly is external financing? Evidence from a structural estimation. The Journal of Finance 62 (4): 1705–1745.
  51. 51 Fang, L. and Peress, J. (2009). Media coverage and the cross‐section of stock returns. The Journal of Finance 64 (5): 2023–2052.
  52. 52 Gomes, J.F. (2001). Financing investment. American Economic Review 91 (5): 1263–1285.
  53. 53 Tumarkin, R. and Whitelaw, R.F. (2001). News or noise? Internet postings and stock prices. Financial Analysts Journal 57 (3): 41–51.
  54. 54 Cao, M., Chychyla, R., and Stewart, T. (2015). Big Data analytics in financial statement audits. Accounting Horizons 29 (2): 423–429.
  55. 55 Subrahmanyam, A. (2019). Big data in finance: evidence and challenges. Borsa Istanbul Review 19: 283–287.

Note

  1. 1 18 journals among the list of journals had published at least two articles during 2000–2019.
..................Content has been hidden....................

You can't read the all page of ebook, please click here login for view all page.
Reset
3.147.66.178