Recommendation Systems on Google Cloud

This course is part of Advanced Machine Learning on Google Cloud Specialization

Instructor: Google Cloud Training

Access provided by Pontificia Universidad Católica del Perú

20,116 already enrolled

7 modules

Gain insight into a topic and learn the fundamentals.

484 reviews

Advanced level

Designed for those already in the industry

Flexible schedule

1 week at 10 hours a week

Learn at your own pace

83%

Most learners liked this course

7 modules

Gain insight into a topic and learn the fundamentals.

484 reviews

Advanced level

Designed for those already in the industry

Flexible schedule

1 week at 10 hours a week

Learn at your own pace

83%

Most learners liked this course

What you'll learn

Devise a content-based recommendation engine.
Implement a collaborative filtering recommendation engine.
Build a hybrid recommendation engine with user and content embeddings.
Use reinforcement learning techniques for contextual bandits in the context of recommendations.

Skills you'll gain

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

5 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your subject-matter expertise

This course is part of the Advanced Machine Learning on Google Cloud Specialization

When you enroll in this course, you'll also be enrolled in this Specialization.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate

There are 7 modules in this course

In this course, you apply your knowledge of classification models and embeddings to build a ML pipeline that functions as a recommendation engine.

This module previews the topics covered in the course.

What's included

1 video1 reading

This module defines what recommendation systems are, reviews the different types of recommendation systems, and discusses common problems that arise when developing recommendation systems.

What's included

5 videos1 reading1 assignment1 discussion prompt

5 videos Total 20 minutes

Introduction 6 minutes
Types of Recommendation Systems 3 minutes
Content-Based or Collaborative 6 minutes
Recommendation System Pitfalls 4 minutes
Discussion 2 minutes

1 reading Total 10 minutes

Recommendation Systems Overview 10 minutes

1 assignment Total 4 minutes

Recommendation Systems Overview 4 minutes

1 discussion prompt Total 20 minutes

Designing a Recommendation System 20 minutes

This module demonstrates how to build a recommendation system using characteristics of the users and items and how to use Qwiklabs to complete each of your labs using Google Cloud.

What's included

8 videos1 reading1 assignment1 app item1 plugin

8 videos Total 24 minutes

Content-Based Recommendation Systems 2 minutes
Similarity Measures 3 minutes
Building a User Vector 4 minutes
Making Recommendations Using a User Vector 2 minutes
Making Recommendations for Many Users 7 minutes
Lab intro: Create a Content-Based Recommendation System 0 minutes
Using Neural Networks for Content-Based Recommendation Systems 4 minutes
Summary 3 minutes

1 reading Total 10 minutes

Content-Based Recommendation Systems 10 minutes

1 assignment Total 4 minutes

Content-Based Recommendation Systems 4 minutes

1 app item Total 90 minutes

Lab: Content-Based Filtering by Hand 90 minutes

1 plugin Total 15 minutes

Accessing and completing labs 15 minutes

This module shows how the data of the interactions between users and items from many different users can be combined to improve the quality of predictions.

What's included

13 videos1 reading1 assignment1 app item

13 videos Total 97 minutes

Types of User Feedback Data 7 minutes
Embedding Users and Items 13 minutes
Factorization Approaches 7 minutes
The ALS Algorithm 5 minutes
Preparing Input Data for ALS 6 minutes
Creating Sparse Tensors For Efficient WALS Input 3 minutes
Instantiating a WALS Estimator: From Input to Estimator 5 minutes
Instantiating a WAL Estimator: Decoding TFRecords 4 minutes
Instantiating a WALS Estimator: Recovering Keys 13 minutes
Instantiating a WALS Estimator: Training and Prediction 6 minutes
Lab Intro: Collaborative Filtering with Google Analytics Data 1 minute
Issues with Collaborative Filtering 22 minutes
Cold Starts 6 minutes

1 reading Total 10 minutes

Collaborative Filtering Recommendations Systems 10 minutes

1 assignment Total 2 minutes

Collaborative Filtering Recommendations Systems 2 minutes

1 app item Total 90 minutes

Lab: Collaborative filtering on Google Analytics Data 90 minutes

This module shows how various recommendation systems can be combined as part of a hybrid approach.

What's included

13 videos1 reading1 assignment1 app item

13 videos Total 62 minutes

Hybrid Recommendation Systems 15 minutes
Lab Intro: Designing a Hybrid Recommendation System 6 minutes
Lab Intro: Designing a Hybrid Collaborative Filtering Recommendation System 4 minutes
Lab Intro: Designing a Hybrid Knowledge-based Recommendation System 5 minutes
Lab Intro: Building a Neural Network Hybrid Recommendation System 0 minutes
Context-Aware Recommendation Systems 8 minutes
Context-Aware Algorithms 5 minutes
Contextual Postfiltering 3 minutes
Modeling Using Context-Aware Algorithms 5 minutes
YouTube Recommendation System Case Study: Overview 3 minutes
YouTube Recommendation System Case Study: Candidate Generation 3 minutes
YouTube Recommendation System Case Study: Ranking 3 minutes
Summary 2 minutes