Stock Price Prediction using Mean Level Corporate Communication Frequency
Gowtham Sethupathi M1, Chaitanya P2, Hariprasath R3, Rathyin V R4, Suresh Kumar M5
1Gowtham Sethupathi M, Department of Computer Science Engineering, SRM Institute of Science and Technology, Chennai, (Tamil Nadu), India.
2Chaitanya P, Department of Computer Science Engineering, SRM Institute of Science and Technology, Chennai, (Tamil Nadu), India.
3Hariprasath R, Department of Computer Science Engineering, SRM Institute of Science and Technology, Chennai, (Tamil Nadu), India.
4Rathyin V R, Department of Computer Science Engineering, SRM Institute of Science and Technology, Chennai, (Tamil Nadu), India.
5Suresh Kumar M, Department of Computer Science Engineering, SRM Institute of Science and Technology, Chennai, (Tamil Nadu), India.
Manuscript received on 13 April 2019 | Revised Manuscript received on 19 May 2019 | Manuscript published on 30 May 2019 | PP: 1233-1239 | Volume-8 Issue-1, May 2019 | Retrieval Number: A3138058119/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Researches in corporate communication network have revealed existence of certain patterns and these patterns can potentially reveal useful information about the organization. Different communication patterns have been formed among different employees of an organization; in this paper we analyze the communication network of an organization to observe the underlying human social behavior that is expressed in an email system. It is a known fact that email systems form a social network. The overall communication pattern in an organization can be directly attributed to its stability and performance; and the stock market value of that organization can be predicted based on the different communication patterns which are obtained from the analysis. These patterns have proved to be successful in helping predict sales value and stock prices. Investing in share market requires lots of study and analysis; and also has certain risks. We use Ensemble model which consists of different prediction models such as ARIMA (Auto Regression Integrated Moving Average), LSTM (Long-Short Term Memory), etc. to predict the stock movements in this model. As Enron Corporations e-mail database is the only corpus publicly available, we use it as the data set for our data mining algorithms.
Index Terms: ARIMA, Communication Pattern, Ensemble Method, Stock Market.
Scope of the Article: Foundations of Communication Networks