Developing mathematical models does convey an impression or perception to the average business person that these tools are highly accurate due to the complexity in creating these tools. This article attempts to dispel this notion by conveying to the reader the accuracy limitations in developing predictive models. At the same time, the author discusses some of the rationale as to why these limitations exist. Yet, even with model accuracy being a limiting factor, these tools still yield tremendous business benefits that accrue right to the bottom line.
predictive analytics data mining Big Data Analytics
This is a preview of subscription content, log in to check access.
Lobo, J.M., Jiménez-Valverde, A. and Real, R. (2008) AUC: A misleading measure of the performance of predictive distribution models. Global Ecology and Biogeography 17 (2): 145–151.CrossRefGoogle Scholar
Stockwell, D.R.B. and Peterson, T.P.A. (2002) Effect of sample size on accuracy of species distribution models. Ecological Modelling 148 (1): 1–13.CrossRefGoogle Scholar
Zou, K.H., O’Malley, A.J. and Mauri, L. (2007) Receiver-operating characteristic analysis for evaluating diagnostic tests and predictive models. Circulation 115 (5): 654–657.CrossRefGoogle Scholar