O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

Building Practical Recommendation Engines – Part 2

Video Description

Use behavioral and historical data to predict the future

About This Video

  • A unique guide that brings you unique projects that will enhance your skills with recommendation engines

  • Make insightful recommendations using various tools in the market

  • Filter information and build end-to-end recommendation engines with the help of Apache Spark, Neo4j, Python, R, and more

  • In Detail

    Recommendation systems allow you to gain insights into data and make a guess on what would be people's preference. It is used all over the web, be it shopping, social networking, or music. This video will teach you how to build unique end-to-end recommendation engines with various tools and enhance your skills.

    You will look at various recommendation engines such as personalized recommendation engines, real-time recommendation engines, SVD recommender systems. You will also get a quick glance into the future of recommendation systems by the end of the video. During the course of the video, you will come across creating recommendation engines with R, Python, Apache Spark, Neo4j, Apache Mahout, and more. By the end of the course, you will also learn the best practices and tricks and tips to build efficient recommender systems.

    Table of Contents

    1. Chapter 1 : Building Personalized Recommendation Engines
      1. The Course Overview 00:03:03
      2. Personalized and Content-Based Recommender System 00:10:22
      3. Content-Based Recommendation Using Python 00:08:16
      4. Context-Aware Recommender Systems 00:02:23
      5. Creating Context Profile 00:04:12
    2. Chapter 2 : Building Real-Time Recommendation Engines with Spark
      1. About Spark 2.0 00:03:44
      2. Spark Core 00:03:33
      3. Setting Up Spark 00:05:12
      4. Collaborative Filtering Using Alternating Least Square 00:03:34
      5. Model Based Recommender System Using pyspark 00:02:19
      6. The Recommendation Engine Approach 00:09:24
      7. Model Evaluation and Selection with Hyper Parameter Tuning 00:10:26
    3. Chapter 3 : Recommendation with Neo4j
      1. Discerning Different Graph Databases 00:07:08
      2. Neo4j 00:03:23
      3. Building Your First Graph 00:04:01
      4. Neo4j Windows Installation 00:01:07
      5. Installing Neo4j on the Linux Platform 00:01:48
      6. Building Recommendation Engines 00:03:05
      7. Generating Recommendations Using Neo4j 00:01:52
      8. Collaborative filtering Using the Euclidean Distance 00:03:38
      9. Collaborative Filtering Using Cosine Similarity 00:02:20
    4. Chapter 4 : Building Scalable Recommendation Engines with Mahout
      1. Setting up Mahout with General Introduction 00:04:21
      2. Core Building Blocks of Mahout 00:10:16
      3. Item-Based Collaborative Filtering 00:02:50
      4. Evaluating Collaborative Filtering with User-Item Based Recommenders 00:03:41
      5. SVD Recommenders 00:01:55
    5. Chapter 5 : The Future of Recommendation Engines
      1. Future and Phases of Recommendation Engines 00:07:52
      2. Using Cases to Look Out for 00:01:58
      3. Popular Methodologies 00:04:47