Applying Ant Colony Optimization for Inducing Decision Tree from Mixed Type of Relational Multiclass Data

Decision trees have been widely used in data mining and machine learning as a comprehensible knowledge representation. Originally the method to construct decision tree follows greedy approach which results in local tree and classification rules. Ant Colony Optimization (ACO) is a metaheuristic approach used to get more optimal solution compared to other methods from large search space. In proposed work we can create a decision tree using Discretization and Pruning method. So we reduce the size of the tree and improve the predictive accuracy. Keywords— decision tree, ant colony optimization, Ant tree miner, Discretization, pruning, proposed method, experiment results, conclusion.