Applying Combinatorial Testing to Data Mining Algorithms
Jaganmohan Chandrasekaran, Huadong Feng, Yu Lei, D. Richard Kuhn, Raghu N. Kacker · 2017
Data mining algorithms are used to analyze and discover useful information from data. This paper presents an experiment that applies Combinatorial Testing (CT) to five data mining algorithms implemented in an open-source data mining software called WEKA. For each algorithm, we first run the algorithm with 51 datasets to study the impact different datasets have on the test coverage. We select one dataset that achieves the highest branch coverage. Next we construct positive and negative combinatorial test sets of configuration options and execute each test set with the selected dataset. Test effectiveness is measured using branch and mutation coverage. Our results suggest that when testing data mining algorithms: (1) larger datasets do not necessarily achieve higher coverage than smaller datasets, (2) test coverage increases progressively slower as test strength increases, and (3) branch coverage correlates well with mutation coverage.