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

The main goal of the ads selection component is to narrow down the set of ads that are relevant for a given query.
In a search-based system, the ads selection component is responsible for retrieving the top relevant ads from the ads database (built using all the active ads in the system) according to the user and query context.
In a feed-based system, the ads selection component will select the top k relevant ads based more on user interests than search terms.

Based on our discussions about the funnel-based approach for modeling, it would make sense to structure the ad selection process in the following three phases:
- **Phase 1:** Quick selection of ads for the given query and user context according to selection criteria
- **Phase 2:** Rank these selected ads based on a simple and fast algorithm to trim ads.
- **Phase 3:** Apply the machine learning model on the trimmed ads to select the top ones.



# Phase 1: Selection of ads
Advertising platforms can have hundreds of millions of active ads. Our main motivation in this phase is to quickly reduce this space from millions of ads to one ads that can be shown to the current user in the given context (e.g. for a user searching  "machine learning" on a mobile device).

The first key requirement to be able to achieve the quick selection objective is to have the ads stored in a system that is fast and enables complex selection criteria. This is where building an in-memory index to store the ads will be massively helpful. Index allows us to fetch ads quickly based on different targeting and relevance information from the user. This is similar to our Search system discussion, where we had to similarly select documents quickly at the selection time to narrow our focus to relevant documents. We will index ads on all possible indexing terms that can be used for selection e.g. targeted terms, city, state, country, region, age etc.

Let's take an example of a search ads system to explain this concept further. Let’s say that a male user, aged twenty-five, and located in San Francisco, California is searching stuff related to machine learning. He types in a query "machine learning". In this case, we would want to select all potential ads that we can show to the user, i.e., the ads targeting criteria matches the user’s profile.

The selection query in this case will look like:




Let’s see what role the ad selection component plays in the overall prediction system.

Introduction

Practical ML Techniques/Concepts

Search Ranking

Feed Based System

Recommendation System

Self-Driving Car: Image Segmentation

Entity Linking System

Ad Prediction System

Ad Selection

Phase 1: Selection of ads