A retail organization’s analytical framework for determining product placement and creating sales promotions for different consumer categories to boost customer loyalty and ultimately benefit is incomplete without considering the significance of Market Basket Analysis. The market is ARM’s well-known activity that is finally utilized to make wise commercial judgments. An essential approach for identifying the often-occurring item set in the transactional dataset is the Apriori algorithm. But it has its weakness i.e., high run time. In this paper, we apply the feature selection technique information gain to find the important features. We analyze the behavior of the Apriori algorithm when applying with and without information gain. The result shows that when using the information gain, the run time of Apriori becomes very low and it returns less number of frequent item sets.