Developing information technologies bring about a huge amount of data which is growing exponentially each day. That large and multidimensional data increases computational costs and makes it difficult to extract meaningful information from the data. Feature selection aims to reduce the multidimensionality of the data while keeping information loss at a minimum level. Different approaches have been proposed for feature selection which may be classified as filter, wrapper, embedded, and hybrid methods. A novel hybrid Feature Selection approach via Ant Colony Optimization Algorithm (FSvACO) is proposed in this paper. The performance of the proposed algorithm is verified by comparing the alternative feature subset selection algorithms in the literature. Additional studies demonstrated that developed FSvACO can eliminate the irrelevant features for most datasets selected from a varied number of features, multi-classes, and a diverse number of instances.