Guest Editors Introduction: Finance Big Data: Management, Analysis, and Applications

Yunchuan Sun, Yufeng Shi, and Zhengjun Zhang, Guest Editors
International Journal of Electronic Commerce,
Volume 23, Number 1, 2019, pp. 9-11.

Big Data is an emerging paradigm in almost all industries. Finance big data (FBD) is becoming one of the most promising areas of management and governance in the financial sector. It is significantly changing business models in financial companies. Many researchers argue that Big Data is fueling the transformation of finance and business at-large in the ways that we cannot as yet assess. A new research area is evolving to study quantitative models and econometric approaches for financial studies that can bridge the gap between empirical finance research and data science. In this fascinating area, experts and scientists can propose novel finance business models by using the Big Data methods, present sophisticated methods for risk control with machine learning tools, provide visualization tools for financial markets analysis, create new finance sentiment indexes by mining public feelings from the massive textual data from social networks, and deploy the information-based tools in other creative ways.

Due to the 4V characteristics of Big Data—volume (large data scale), velocity (real-time data streaming), variety (different data formats), and veracity (data uncertainty)—a long list of challenges for FBD management, analytics, and applications exists. These challenges include (1) to organize and manage FBD in effective and efficient ways; (2) to find novel business models from FBD analytics; (3) to handle traditional finance issues like high-frequency trading, sentiments, credit risk, financial analysis, risk management and regulation, and others, in creative Big Data–driven ways; (4) to integrate the variety of heterogeneous data from different sources; and (5) to ensure the security and safety of finance systems and to protect the individual privacy in view of the availability of Big Data. To meet these challenges, we need fundamental research on both data analytics technology and finance business.

This special issue, “Finance Big Data: Management, Analysis, and Applications,” of International Journal of Electronic Commerce, is motivated by the need to meet the challenges of the fast development of finance big data. The papers brought together in this special issue highlight research efforts focused on the development of methods, tools, and techniques for the handling of various aspects of FBD from academia and industries.

Viktor Manahov and Hanxiong Zhang, in “Forecasting Financial Markets Using High-Frequency Trading Data: Examination with Strongly Typed Genetic Programming,” develop an artificial futures market populated with high-frequency (HF) traders and institutional traders using Strongly Typed Genetic Programming trading algorithm. The authors simulate real-life futures trading at the millisecond time frame by applying Strongly Typed Genetic Programming to E-Mini S&P 500 data stamped at the millisecond interval. A direct forecasting comparison between HF traders and institutional traders indicate the superiority of the former. They observe that the negative implications of HF traders in futures markets can be mitigated by introducing a minimum resting trading period of fewer than 50 milliseconds.

In their paper “Virtual Standard Currency for Approximating Foreign Exchange Rates,” Hongxuan Huang and Zhengjun Zhang propose a new wealth measure: the virtual standard currency (VSC), as a methodology to objectively measure the wealth in a currency portfolio. The VSC is regarded as a virtual base currency such that any real foreign exchange rate matrix is approximated by a rank one matrix consisting of two virtual exchange rate vectors. The existence of the VSC is proved through an optimal solution to the basic rank one approximation problem. The evaluation of wealth in a currency portfolio is free from the buying or selling operations in real currencies so that the currency portfolio is kept invariant during the measurement. The VSC can eliminate uncertainties arising from the choice of a particular real currency and the interactive effects across different kinds of currencies. In addition, the modified power method is designed to search for the virtual exchange rates numerically, the convergence of which is also established. Furthermore, some practical examples are presented to verify the feasibility and efficiency of the modified power method in approximating a foreign exchange rate matrix.

Rongcai Hu, Meng Liu, Pingping He, and Yong Ma, in “Can Investors on P2P Lending Platforms Identify Default Risk?” use the data from to examine the relationship between the interest rates on borrowings and the default risks of borrowers. They find that there is an asymmetry between the interest rate and default risk. That is, orders with the same interest rate may have different default risks. Their empirical results also show two conclusions contrary to common sense: The higher a borrower’s income, the greater the default risk, and the pattern describing the relationship between the default risk and the age of the borrower is U-shaped. Furthermore, the authors find that investors may make mistakes about the relationship between certain information of a borrower and the default risk, but they could identify the default risk of the borrower as long as they have a good knowledge of the main factors affecting the default risk, which are the amount, the term, and the borrower’s credit risk level.

In the paper “How Do the Global Stock Markets Influence One Another? Evidence from Finance Big Data and Granger Causality Directed Network,” Yong Tang, Jason Jie Xiong, Yong Luo, and Yi-Cheng Zhang apply the Granger causality test to build the Granger Causality Directed Network for 33 global major stock market indices to study how the markets influence one another by investigating the directed edges in the different filtered networks. The network topology that evolves in different market periods is analyzed via a sliding window approach and FBD visualization. By quantifying the influences of market indices, 33 global major stock markets from the Granger causality network are ranked in comparison with the result based on PageRank centrality algorithm. Results reveal that the ranking lists are similar in both approaches where the United States indices dominate the top position followed by other American, European indices, and Asian indices. The lead-lag analysis reveals there are lag effects among the global indices. The result sheds new insights on the influences among global stock markets with implications for trading strategy design, global portfolio management, risk management, and markets regulation.


We thank all of the authors for their valuable contributions to this special issue and all of the reviewers for their hard work, which helped us further enhance the quality of the issue. We are indebted to Professor Vladimir Zwass, Editor-in-Chief of the journal, who has provided the greatest support to the special issue. Finally, we express our sense of honor to serve as the guest editors of this issue.