Corporate Communication Network and Stock Price Movements Insights From Data Mining
Grounded on communication theories, we propose to use a data-mining algorithm to detect communication patterns within a company to determine if such patterns may reveal the performance of the company. Specifically, we would like to find out whether or not there exist any association relationships between the frequency of e-mail exchange of the key employees in a company and the performance of the company as reflected in its stock prices. If such relationships do exist, we would also like to know whether or not the company’s stock price could be accurately predicted based on the detected relationships. To detect the association relationships, a data-mining algorithm is proposed here to mine e-mail communication records and historical stock prices so that based on the detected relationship, rules that can predict changes in stock prices can be constructed. Using the data-mining algorithm and a set of publicly available Enron e-mail corpus and Enron’s stock prices recorded during the same period, we discovered the existence of interesting, statistically significant, association relationships in the data. In addition, we also discovered that these relationships can predict stock price movements with an average accuracy of around 80%. The results confirm the belief that corporate communication has identifiable patterns and such patterns can reveal meaningful information of corporate performance as reflected by such indicators as stock market performance. Given the increasing popularity of social networks, the mining of interesting communication patterns could provide insights into the development of many useful applications in many areas.
The existence of interesting communication patterns among different participants of different social network platforms. These patterns have been shown to be useful in predicting product sales and stock prices. Compared to a social network, which can be considered as representing connections among people in the public, a corporate network connects only employees in a big corporation.While participants of a social network can express opinions on any issues of interest, members of a corporate communication network are expected to mainly talk about company-specific business. If human communication patterns can be discovered in the social networks to predict products sales or stock performance, one may wonder if such patterns also exist among members in corporate communication network to allow the same to be done. Unlike social networks, in a corporate communication network, e-mails have long been used as a tool for inter-organizational and intra-organizational information exchange. In the same way, a social network platform is able to capture participants’ behavior and their opinions about various issues and events.
In this paper, we propose that a company’s performance, in terms of its stock price movement, can be predicted by internal communication patterns. To obtain early warning signals, we believe that it is important for patterns in corporate communication networks to be detected earlier for the prediction of significant stock price movement to avoid possible adversities that a company may face in the stock market so that stakeholders’ interests can be protected as much as possible. Despite the potential importance of such knowledge about corporate communication, little work has been done in this important direction. It is for this reason that we are proposing in this paper to make use of a computational approach to determine if patterns detected in a corporate communication network are related to corporate performance. In other words, employee communication can serve a critical “business function that drives performance and contributes to a company’s financial success”.
The findings and theoretical implications from this paper are twofold. On one hand, we captured the communications among nodes in Enron’s major corporate communication network and identified employees’ communication patterns. This paper demonstrates that a corporate e-mail ecosystem contains meaningful information about employees’ communication patterns. Even if we only focus on the communication frequency, a company (Enron in our case) has identifiable patterns of e-mail exchange. Such identifiable patterns can reveal important information about major corporate activities and organizational stability that may subsequently influence the focal company’s performance in the stock market. Therefore, cooperate communication patterns can serve as a good proxy to predict a company’s stock performance. Our experimental results demonstrated the existence of dependence between e-mail communication network and stock price for Enron. This paper extended the existing communication theories to capture the patterns of corporate communication and the focal company’s stock performance. On the other hand, social networks have become a hot topic in the field of data mining recently. In this paper, we not only provided an innovative idea on using data-mining algorithms but also constructed the relationship between social network and finance. Hence, this paper demonstrated great potential to predict the amounts of increases and decreases of stock price based on the weighted rules.
 G. Miller, “Social scientists wade into the tweet stream,” Science, vol. 333, no. 6051, pp. 1814–1815, 2011.
 W. Duan, B. Gu, and A. B. Whinston, “Do online reviews matter?— An empirical investigation of panel data,” Decision Support Syst., vol. 45, no. 4, pp. 1007–1016, 2008.
 B. Li, K. C. C. Chan, and C. Ou, “Public sentiment analysis in Twitter data for prediction of a company’s stock price movements,” in Proc. IEEE Int. Conf. e-Bus. Eng. (ICEBE), Nov. 2014, pp. 232–239.
 B. Collingsworth, R. Menezes, and P. Martins, “Assessing organizational stability via network analysis,” in Proc. IEEE Symp. Comput. Intell. Financial Eng., Mar. 2009, pp. 43–50.
 D. J. Barrett, “Change communication: Using strategic employee communication to facilitate major change,” Corporate Commun., Int. J., vol. 7, no. 4, pp. 219–231, 2002.
 K. Yates. (2003). Effective Employee Communication Linked to Greater Shareholder Returns, Watson Wyatt Study Finds. Accessed: Nov. 2003. [Online]. Available: http://www.watsonwyatt.com/render.asp?catid= 1&id=12092
 M.-C.Wu, S.-Y. Lin, and C.-H. Lin, “An effective application of decision tree to stock trading,” Expert Syst. Appl., vol. 131, no. 2, pp. 270–274, 2006.
 E. Vamsidhar, K. V. S. R. P. Varma, P. S. Rao, and R. Satapati, “Prediction of rainfall using backpropagation neural network model,” Int. J. Comput. Sci. Eng., vol. 2, no. 4, pp. 1119–1121, 2010.
 C. W. Down, G. C. Phillip, and A. L. Pfeiffer, “Communication and organizational outcomes,” in Handbook of Organizational Communication, G. Goldhaber and G. Barnett, Eds. Norwood, NJ, USA: Ablex, 1988.
 P. G. Clampitt and C. W. Downs, “Employee perceptions of the relationship between communication and productivity: A field study,” J. Bus. Commun., vol. 30, no. 1, pp. 5–28, 1993.
 G. S. Hansen and B. Wernerfelt, “Determinants of firm performance: The relative importance of economic and organizational factors,” Strategic Manage. J., vol. 10, no. 5, pp. 399–411, 1989.  W. W. Burke and G. H. Litwin, “A causal model of organizational performan
ce and change,” J. Manage., vol. 18, no. 3, pp. 523–545, 1992.
 R. Katz and M. Tushman, “Communication patterns, project performance, and task characteristics: An empirical evaluation and integration in an R&D setting,” Org. Behav. Hum. Perform., vol. 23, no. 2, pp. 139–162, 1979.
 E. Gilbert and K. Karahalios, “Widespread worry and the stock market,” in Proc. 4th Int. AAAI Conf. Weblogs Social Media (ICWSM), 2010, pp. 59–65.
 R. Katz, “The effects of group longevity on project communication and performance,” Admin. Sci. Quarterly, vol. 27, no. 1, pp. 81–104, 1982.