Start Date
12-13-2015
Description
Traditional economic and business forecasting about corporate credit has relied on statistics from government agencies, annual reports and financial statements. These statistics are often published with significant delay, which limits their usefulness for predicting changes in creditworthiness. Yet, a delay in responding to changes in a company’s credit rating can have significant financial and risk consequences. With the widespread adoption of search engines, social media and related information technologies, it is possible to obtain data on literally trillions of economic decisions almost the instant that they are made. In this study, we investigated the power of these online activity data combined with data on firms’ business ecosystem to predict the likelihood of counterparty credit downgrade risk. The research offers a novel approach that contributes to the fields of information systems, finance, and social science by providing new insights on the role of these data types on firms’ financial risk.
Recommended Citation
Ghasemkhani, Hossein; Reichman, Shachar; and Westerman, George, "Using Predictive Analytics to Reduce Uncertainty in Enterprise Risk Management" (2015). ICIS 2015 Proceedings. 20.
https://aisel.aisnet.org/icis2015/proceedings/DecisionAnalytics/20
Using Predictive Analytics to Reduce Uncertainty in Enterprise Risk Management
Traditional economic and business forecasting about corporate credit has relied on statistics from government agencies, annual reports and financial statements. These statistics are often published with significant delay, which limits their usefulness for predicting changes in creditworthiness. Yet, a delay in responding to changes in a company’s credit rating can have significant financial and risk consequences. With the widespread adoption of search engines, social media and related information technologies, it is possible to obtain data on literally trillions of economic decisions almost the instant that they are made. In this study, we investigated the power of these online activity data combined with data on firms’ business ecosystem to predict the likelihood of counterparty credit downgrade risk. The research offers a novel approach that contributes to the fields of information systems, finance, and social science by providing new insights on the role of these data types on firms’ financial risk.