Recommendation system

Sanket Lolge   22 January,2021  

A recommendation system , also known as a recommender engine , is software that analyzes available data to make suggestions for something that a website user might be interested in, such as a book, a video or a job, among other possibilities. An engine, in a software context, is a special-purpose program that performs a task through a variable algorithm, often as a feature of some larger program.

A search engine is one type of recommendation engine, responding to search queries with pages of results that are (at least theoretically) the search engine's best suggestions for websites that satisfy the user's query, based on the search term plus other data, such as location and trending topics.



Why we use recommender systems?

A recommender system usually employs data sources to learn more about such preferences, making good use of explicit feedback resulting from diverse evaluation metrics such as “Add To Favorites” for example, or implicit feedback deriving from the number and length of content-based interactions.   

Within the implicit feedback approach, a basic algorithm despite being more elaborate than the one which generates completely random recommendations, consists of reflecting most popular content, summing up all user activity and recommending most common content in relation to the number and length of visits.

Recommender systems are really critical in some industries as they can generate a huge amount of income when they are efficient or also be a way to stand out significantly from competitors. As a proof of the importance of recommender systems, we can mention that, a few years ago, Netflix organised a challenges (the “Netflix prize”) where the goal was to produce a recommender system that performs better than its own algorithm with a prize of 1 million dollars to win.



Personalization in recommender system is the creation of custom alternatives that meets the individual customer’s preferences based on the human behaviour and the domain knowledge. Human behaviour is defined as “the potential and expressed capacity for physical, mental and social activity during the phases of human life” and by definition, domain knowledge is the knowledge specific to a “particular field of thought, activity or interest especially one over which someone has control, influence or rights”.

The human behavioural inclination to the domain varies. Personalization in recommender systems is achieved by delivering relevant, tailored experience to the right user at the right time on the right device meeting the individual user needs by combining historical, behavioural and profile data with real-time situational feedback and there by exploiting recommenders as a personalization tool tailoring products / services of interest to the users.


How Do Recommender Systems Work?

Understanding Relationships

Relationships provide recommender systems with tremendous insight, as well as an understanding of customers. There are three main types that occur:

User-Product Relationship

The user-product relationship occurs when some users have an affinity or preference towards specific products that they need. For example, a cricket player might have a preference for cricket-related items, thus the e-commerce website will build a user-product relation of player->cricket.

Product-Product Relationship

Product-product relationships occur when items are similar in nature, either by appearance or description. Some examples include books or music of the same genre, dishes from the same cuisine, or news articles from a particular event.

User-User Relationship

User-user relationships occur when some customers have similar taste with respect to a particular product or service. Examples include mutual friends, similar backgrounds, similar age, etc.


Data & Recommender Systems

In addition to relationships, recommender systems utilize the following kinds of data:

User Behavior Data

Users behavior data is useful information about the engagement of the user on the product. It can be collected from ratings, clicks and purchase history.

User Demographic Data

User demographic information is related to the user’s personal information such as age, education, income and location.

Product Attribute Data

Product attribute data is information related to the product itself such as genre in case of books, cast in case of movies, cuisine in case of food.


"Too few choices are bad but too many choices can lead to paralysis"

Have you heard about the famous Jam Experiment? In 2000, psychologists Sheena Iyengar and Mark Lepper from Columbia and Stanford University presented a study based on their field experiment. On a regular day, consumers shopping at an upscale grocery store at a local food market were presented with a tasting booth which displayed 24 varieties of Jam. On some other day, the same booth displayed only 6 varieties of Jam. The experiment was being conducted to adjudge which booth would garner more sales and it was assumed that more varieties of jam would fetch more people to the counter thereby getting more business. However, a strange phenomenon was observed. Whereas the counter with 24 jams generated more interest, their conversion to sales was pretty low(about 10 times lower) as compared to the 6 jams counter.



Every Successful Product Or Business Has A Strong Recommendation Engine At Its Core.

Amazon’s — “Customers who bought this item also bought…”.

Netflix’s — “Other Movies You May Enjoy…”

Spotify’s — “Recommended songs…”

Google’s — “Visually Similar Images…”

YouTube’s — “Recommended Videos…”

Facebook’s — “People You May Know…”

LinkedIn’s — “Jobs You May Be Interested In…”

are all results of strong recommendation systems at the core of these businesses. The impact of these recommendation systems is immense from a business standpoint as well.