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

# Why do you need diverse Tweets?

Let's assume that you adopted the following modelling option for your Twitter feed ranking system. The Tweet selection component will select one-hundred thousand Tweets for user A's Twitter feed. The stage one ranker will choose the top five-hundred most engaging Tweets for user A. The stage two ranker will then focus on assigning engagement probabilities to these Tweets with a higher degree of accuracy. Finally, the Tweets will be sorted according to the engagement probability scores and will be ready for display on the user's Twitter feed.   

Consider a scenario where the sorted list of Tweets has five consecutive posts by the same author. No, your ranking model hasn't gone bonkers! It has rightfully placed these tweets at the top because:
- The logged-in user and the Tweet's author have frequently interacted with each other's Tweets
- The logged-in user and the Tweet's author have a lot in common like hashtags followed and common followees
- The author is very influential, and their Tweets generally gain a lot of traction

> 📝 This scenario remains the same for any modelling option.

## Diversity in Tweets' authors

However, no matter how good of a friend the author is or how interesting their Tweets might be, user A would eventually get bored of seeing Tweets from the same author repeatedly. Hence, you need to introduce diversity with regards to the Tweets' author.

## Diversity in tweets' content
Another scenario where we might need to introduce diversity is the Tweet's content. For instance, if your sorted list of Tweets has four consecutive tweets that have videos in them, the user might feel that their feed has too many videos. 


# Introducing the repetition penalty
To rid the Twitter feed from a monotonous and repetitive outlook, we will introduce a repetition penalty for repeated Tweet authors and media content in the Tweet.

One way to introduce a repetition penalty could be to add a negative weight to the Tweet's score upon repetition. For instance, in the following diagram, whenever you see the author being repeated, you add a negative weight of $-0.1$ to the Tweet's score.
 




Let's learn methods to reduce monotony on the user's Twitter feed.

Introduction

Practical ML Techniques/Concepts

Search Ranking

Feed Based System

Recommendation System

Self-Driving Car: Image Segmentation

Entity Linking System

Ad Prediction System

Diversity

Why do you need diverse Tweets?