Intelligent automated decision support systems are now found to be very much useful in various fields. In Bioinformatics and machine learning in general, there is a large variation in the predictive measures that are used to evaluate intelligent systems. If we do not assess the accuracy of model’s prediction, a vital step in model development, application of it will have little merit. This work critically discusses different approaches to assess predictive performance and various test statistics. Choice of assessing strategy or validation for a specific application helps determine the suitability of the model and to compare performance of different modeling techniques. The purpose of this article is to serve as an introduction to different important bench marking parameters and as a guide for using them in research, such as -
Predictive performance, Confusion Matrix, Receiver operating characteristic (ROC),
Akaike information criteria (AIC), Kappa statistic, Lift, Cumulative gain, Probability Threshold.
Full paper available at:
International Journal of Computer Science and Engineering,
Volume-3, Special Issue-1. E-ISSN:2347-2693.