Your proven path to success in Machine Learning Interviews – developed by FAANG engineers. Unlock ML loops at top companies with a System Design approach.

System design is an important component of any ML interview. Being able to efficiently solve open-ended machine learning problems is a key skill that can set you apart from other engineers and increase the level of seniority at which you’re hired.

This course helps you build that skill, and goes over some of the most popularly asked interview problems at big tech companies. You’ll walk step-by-step through solving these problems, focusing in particular on how to design machine learning systems rather than just answering trivia-style questions. 

Once you’re done with the course, you’ll be able to not just ace the machine learning interview at any tech company, but impress them with your ability to think about systems at a high level. If you have a machine learning or system design interview coming up, you’ll find the course tremendously valuable.

Grokking the Machine Learning Interview

# Introduction

Recommendation systems are used by most of the platforms we use daily. 

For example:
1. The Amazon homepage recommends personalized products that we might be interested in.
2. The Pinterest feed is full of pins that we might like based on trends and our historical browsing.
3. Netflix shows movie recommendations based on our taste, trending movies, etc.

In this chapter, we will go over the Netflix movie recommendation problem, but a similar technique can be applied to nearly all other recommendation systems.

# Problem statement

The interviewer has asked you to **display media (movie/show) recommendations for a Netflix user.** Your task is to make recommendations in such a manner that the chance of the user watching them is maximized. 


# Visualizing the problem

The prime factor that led to Netflix's success was its recommendation system. The algorithm does a great job of bringing the right kind of content to the right users. 
Unlike Netflix's recommendation system, a simple recommendation system would have simply recommended the trending movies/shows with little regard for the particular user's preferences. At most, it would look at the viewer's past watches and recommend movies/shows of the same genre. 

Another key aspect of Netflix's approach is that they have found ways to recommend content that seemed different from the user's regular choices. However, Netflix’s recommendations are not based on wild guesses, but they are based on *other users' watch histories*, these users share some common patterns with the concerned user. This way, customers got to discover new content that they wouldn't have found otherwise.

> 📝 80% of the shows watched on Netflix are driven by its recommendations, as opposed to someone searching for a particular show and watching it.

The task at hand is to create such a recommendation system that keeps the viewers hooked and introduces them to varied content that expands their horizons.


# Scope of the problem 

Now that you know the problem at hand, let’s define the scope of the problem:

1. The total number of subscribers on the platform as of 2019 is 163.5 million. 
2. There are 53 million international daily active users.

Hence, you have to build a system for a large number of users who require good recommendations on a daily basis. 

One common way to set up the recommendation system in the machine learning world is to pose it as a classification problem with the aim to predict the probability of user engagement with the content. So, the problem statement would be:  
_<center>"Given a user and context (time, location, and season), predict the probability of engagement for each movie and order movies using that score."</center>_

Let's get acquainted with the task of building a recommendation system. 

Problem Statement

Let's get acquainted with the task of building a recommendation system.

Introduction

Practical ML Techniques/Concepts

Search Ranking

Feed Based System

Recommendation System

Self-Driving Car: Image Segmentation

Entity Linking System

Ad Prediction System

Problem Statement

Introduction

Problem statement

Visualizing the problem

Scope of the problem