Rule pruning techniques in the ant-miner classification algorithm and its variants: A review

Rule-based classification is considered an important task of data classification. The ant-mining rule-based classification algorithm, inspired from the ant colony optimization algorithm, shows a comparable performance and outperforms in some application domains to the existing methods in the literature. One problem that often arises in any rule-based classification is the overfitting problem. Rule pruning is a framework to avoid overfitting. Furthermore, we find that the influence of rule pruning in ant-miner classification algorithms is equivalent to that of local search in stochastic methods when they aim to search for more improvement for each candidate solution. In this paper, we review the history of the pruning techniques in ant-miner and its variants. These techniques are classified into post-pruning, pre-pruning and hybrid-pruning. In addition, we compare and analyse the advantages and disadvantages of these methods. Finally, future research direction to find new hybrid rule pruning techniques are provided.