Item-based Hybrid Recommender System for newly marketed pharmaceutical drugs

Recommender systems are Information systems that predict user preferences and present product/item/service recommendations that are personalized and subjective. These systems have been extant in the field of e-commerce and research extensively. Our work intends to introduce such a perceptive system to the field of healthcare. New drugs and their variants enter the market quite so often and keeping track of each of them is a tedious task. Hence, the usage of such new drugs is skewed. Our system aims at insightfully recommending the new drugs, thereby enlightening the medical community on the newest introductions to the market. The working flow follows the ensuing steps: Gather information on every drug that forays into the market based on criteria such as its generic name, brand name and the purpose it serves and also gather user information through a sign-up survey form; Employing item-based Top-N recommendation algorithm to compare and contrast search histories of users with a common background and determining item-item similarities based on product features; ultimately Top-N recommendations are then presented to the user.