Discriminative feature combination selection for enhancing multiclass classification

Frequent pattern mining is commonly utilized to generate combined-feature candidates, yet many are non-discriminative and thus might be useless for predictive models. In this paper, we propose to use feature combinations derived from frequent patterns to obtain more accurate multiclass classification models. Specifically, we present a novel mathematics inference to show what are discriminative feature combinations. Hence, an efficient algorithm is proposed for mining and selecting discriminative patterns. Experimental results on twenty UCI datasets demonstrate that the proposed method can help to improve the classification performance remarkably, compared with other baseline methods. Moreover, an internal evaluation is employed to validate the strong discriminative power of our feature combinations.