How Netflix implemented Artificial Intelligence to manage its Recommendation SystemEstimated Reading Time: just 3 min

Artificial Intelligence (AI) is the intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and other living beings.

For a machine acting like a human means being able to perform 5 macro-functions:

• Perception (recognizing and interpreting reality)
• Reasoning (drawing new conclusions)
• Planning (detecting patterns and adapting to new environments)
• Knowledge Representation (extract and store knowledge)
• Natural Language Processing (communicate successfully in a human language)

AI research started in 1956 after a workshop at Dartmouth College and its fathers where:

• Allen Newell and Herbert Simon from CMU
• John McCarthy and Marvin Minsky from MIT
• Arthur Samuel from IBM

Dartmouth College group focused on Restricted AI that solves only one of the 5 acting like a human macro-functions at a time.

Recently, a huge breakthrough came with the birth of Machine Learning.

Machine Learning is a field of artificial intelligence that uses statistical techniques to give computer systems the ability to learn from data, without being explicitly programmed.

This step ahead allowed systems to solve problems that involve:

• Supervised Learning
• Clustering
• Dimensionality Reduction
• Structured Prediction
• Anomaly Detection

Another breakthrough came with Deep Learning.

Deep Learning is a subset of Machine Learning that, using architectures based on Neural Networks, allows machines to learn a large variety of activities as humans do.

This step ahead allowed systems to solve problems that involve:

• Supervised/Semi-Supervised/Unsupervised Learning
• Image/Audio Recognition
• Natural Language Processing

Nowadays, there are 3 main problems that can be solved with AI

1. Regression Problems: this could be applied whenever the output of a subset of inputs is a continuous function
2. Classification Problems: this could be applied whenever the output of a subset of inputs is a discrete function
3. Clustering Problems: this could be applied whenever the output of a subset of inputs is not predictable/known

The 3 problems are solved by using sequences of algorithms called Neural Networks.

Usually, every Neural Network performs 4 activities:

1. Data Collection
2. Data Cleaning
3. Patterns Identification
4. Prediction Making

One of the most interesting applications of Artificial Intelligence is Netflix Recommendation System.

Netflix is a media-services provider headquartered in Los Gatos, California.

It was founded in August 1997 by Reed Hastings and Marc Randolph who, inspired by Amazon, wanted to find a category that could be sold over the internet using a similar business model.

Therefore, Netflix started renting DVDs that were first introduced in the United States in March 1997. The available titles were 925 and they made almost the whole available catalogue.

Since the beginning, the co-founders of Netflix considered to eliminate the physical copies of DVDs and they wanted to offer movies online even though that was made impossible by the slow internet connection of that time.

But when Hastings and Randolph discovered Youtube in 2005, they started working on the digital business model that became truth in February 2007 when the company moved to provide video on demand.

In 2009, Netflix was able to offer 12,000 titles but there was a huge problem with the usage of the Catalog Size.

In fact, the Effective Catalogue Size was small since the users used to watch movies with high rating without considering the underrated ones that may have been aligned with their taste.

At this point, Netflix introduced Cinematch, a deep learning-based recommendation system based.

The algorithm works on 2 levels:

• It solves a Clustering Problem per each user by building a subset of people with the same tastes based on their actions and preferences
• It solves a Classification Problem per each user by suggesting contents that other people with a similar watching history likes

Since the introduction of Cinematch, the effective catalogue size increased 4 times making Netflix able to satisfy:

• Users that could watch new interesting content
• Studios that were considered minor since they got visibility

The company grew through the years having in 2017

• More than 5 thousand employees
• More than US$ 11 billion of Revenues

The Artificial Intelligence Recommendation System by Netflix has super-human powers because of its ability to:

• Process a large amount of data (Netflix would have thousands doing this manually)
• Operate consistently 24/7