Start Date
12-18-2013
Description
While much research work has been devoted to analysis and prediction of individuals’ behavior in social networks, very few studies about the analysis of business networks are conducted. Empowered by recent research on automated mining of business networks, this paper illustrates the design of a novel business network-based model called Energy Cascading Model (ECM) for the analysis and prediction of business performance using the proxies of stock prices. More specifically, the proposed prediction model takes into account both influential business relationships and twitter sentiments of firms to infer their stock price movements. Our empirical experiments based on a publicly available financial corpus and social media postings reveal that the proposed ECM model is effective for the prediction of directional stock price movements. The business implication of our research is that business managers can apply our design artifacts to more effectively analyze and predict the potential business performance of targeted firms.
Recommended Citation
Zhang, Wenping and Lau, Raymond, "THE DESIGN OF A NETWORK-BASED MODEL FOR BUSINESS PERFORMANCE PREDICTION" (2013). ICIS 2013 Proceedings. 10.
https://aisel.aisnet.org/icis2013/proceedings/KnowledgeManagement/10
THE DESIGN OF A NETWORK-BASED MODEL FOR BUSINESS PERFORMANCE PREDICTION
While much research work has been devoted to analysis and prediction of individuals’ behavior in social networks, very few studies about the analysis of business networks are conducted. Empowered by recent research on automated mining of business networks, this paper illustrates the design of a novel business network-based model called Energy Cascading Model (ECM) for the analysis and prediction of business performance using the proxies of stock prices. More specifically, the proposed prediction model takes into account both influential business relationships and twitter sentiments of firms to infer their stock price movements. Our empirical experiments based on a publicly available financial corpus and social media postings reveal that the proposed ECM model is effective for the prediction of directional stock price movements. The business implication of our research is that business managers can apply our design artifacts to more effectively analyze and predict the potential business performance of targeted firms.