Machine learning algorithms form the core of all our products. Machine learning is a subarea of Artificial Intelligence that help computers to learn themselves. Recommendation engines, face detection and voice recognition are some applications of Machine learning.
ExpertRec recommendation engine is based on Expectation Maximization. It presents the user with choices that maximises the probability (Expectation) of a favorable action (say a buy). Since it takes into account, not only the user behavior, but also the behaviors of the device, widgets, it optimizes the end goal leaving behind traditional algorithms like collaborative filtering and content based filtering.
In CF systems a user is recommended items based on the past ratings of all users collectively. It is a model-based algorithm for making recommendations. In the algorithm, the similarities between different items in the dataset are calculated by using one of a number of similarity measures, and then these similarity values are used to predict ratings for user-item pairs not present in the dataset.
Content-based filtering, recommends items based on a comparison between the content of the items and a user profile. Keywords are used to describe the items; beside, a user profile is built to indicate the type of item this user likes. Various candidate items are compared with items previously rated by the user and the best-matching items are recommended.