Background: The majority of software faults are present in small number of modules, therefore accurate prediction of fault-prone modules helps improve software quality by focusing testing efforts on a subset of modules. Aims: This paper evaluates the use of the faults-slip-through (FST) metric as a potential predictor of fault-prone modules. Rather than predicting the fault-prone modules for the complete test phase, the prediction is done at the specific test levels of integration and system test. Method: We applied eight classification techniques, to the task of identifying fault prone modules, representing a variety of approaches, including a standard statistical technique for classification (logistic regression), tree-structured classifiers (C4.5 and random forests), a Bayesian technique (Naive Bayes), machine-learning techniques (support vector machines and back-propagation artificial neural networks) and search-based techniques (genetic programming and artificial immune recognition systems) on FST data collected from two large industrial projects from the telecommunication domain. Results: Using area under the receiver operating characteristic (ROC) curve and the location of (PF, PD) pairs in the ROC space, the faults slip-through metric showed impressive results with the majority of the techniques for predicting fault-prone modules at both integration and system test levels. There were, however, no statistically significant differences between the performance of different techniques based on AUC, even though certain techniques were more consistent in the classification performance at the two test levels. Conclusions: We can conclude that the faults-slip-through metric is a potentially strong predictor of fault-proneness at integration and system test levels. The faults-slip-through measurements interact in ways that is conveniently accounted for by majority of the data mining techniques.