1.1 RECOMMENDATION SYSTEM
Social network allow users to post
ratings and reviews and to notify friends of these posts. As our
social lives increasingly flow from the real world to the online world, now a
days we prefer online shopping instead of going to shop which saves our time
and discounts for any products is been notified to the user via email, text
Recommendation systems provide users with
suggestions about products. One popular category of recommendation systems is
collaborative filtering systems that try to predict the utility of items. Items
are recommended based on the preferences of the users. Time based information
of the user ratings towards improving the predictions in collaborative
recommendation systems. Recommender systems typically provide a user with a
list of recommended items she may be interested in, or predict how much she might
prefer each item. These systems help users to decide on appropriate items, and
ease the task of finding preferred items in a collection.
It is one
of the technologies used to build recommendations on the Web. Some
popular websites that make use of the collaborative filtering technology
include Amazon, Netflix, and iTunes. Collaborative
filtering method requires ratings for an item to make a prediction. Rating is
an association of a user and an item by means of a value. Rating can be either
explicit or implicit. Explicit rating requires the user to rate an item.
Implicit rating infers a user’s preference from his or her actions. If a user
visits a product page, then he might have an interest in buying the product but
if he ends up buying the product, then it inferred that the user has a very
strong interest in similar products.
filtering method is used to making automatic predictions about the
interests of a user by collecting preferences or taste information from many users.
1.2.1 Memory Based
This approach uses user rating data to
compute the similarity between users or items. This is used for making
recommendations. This was an early approach used in many commercial systems.
It’s effective and easy to implement, simple, fast, and self explanatory.
These algorithms utilize the entire
user-item database to generate a prediction. These systems introduce
statistical techniques to find a set of users and neighbors that have a history of agreeing with
the target user, they either rate different items similarly or they tend to buy
similar sets of items. Once a group of users is formed, these systems use
different algorithms to combine the preferences of users to produce a
prediction for the active user. It is also called as nearest-neighbor collaborative
filtering or user-based collaborative filtering. These are more popular and