The Item-based Collaborative Filtering Technique is a recommendation algorithm that recommends things based on the similarity between items. This study will focus on enhancing the Item-based Collaborative Filtering algorithm concerning the diversity of the recommendations. This paper introduces an enhanced version of the algorithm in which K-Nearest Neighbors and Interquartile Range Theory was implemented, wherein this diversifies the final list of recommendations to the user. These methods prevent the researchers from recommending items from a narrow spectrum of users' interests. Compared to the typical IBCF, the study shows that the methods used effectively make the recommended items diversified.