Description

This comprehensive course will guide you to use the power of Python to evaluate recommender system datasets based on user ratings, user choices, music genres, categories of movies, and their years of release with a practical approach to build content-based and collaborative filtering techniques for recommender systems with hands-on experience.

Recommender systems are algorithms that suggest relevant items to users (movies, books, products, or a service). Recommender systems are critical in specific industries to generate massive incomes efficiently or stand out significantly from competitors. The course begins with basic recommender system concepts. You will learn important recommender system taxonomies and recommender system mechanism development using machine and deep learning with Python. Python as a programming language will be taught in this course to implement machine and deep learning concepts efficiently. You will model a k-nearest neighbor-based recommender engine for various applications and know the pros and cons of deep learning-based mechanisms. You will build a recommender system for apps such as Spotify and explore neural collaborative filtering and variational auto-encoders for collaborative filtering. You will explore various matrices (item context, user rating, and error). You will understand recommender system quality, online/offline evaluation techniques, dataset partitioning, and overfitting. Upon completing the course, you will understand the roles and impacts of recommender systems in real-world applications with a unique hands-on experience in developing complete recommender system engines for customized datasets in various projects. All resources are available at: https://github.com/PacktPublishing/Recommender-Systems-Complete-Course-Beginner-to-Advance

What You Will Learn

Explore recommender systems with integrated artificial intelligence
Build item-based recommender systems with machine learning/Python
Understand the pros and cons of deep learning in recommender systems
Learn the basic neural network models for recommendations
Understand the mechanism of generic deep learning-based approaches
Implement two-tower models for developing a recommender system

Audience

This course is designed for individuals wanting to advance their applied machine/deep learning and master data analysis; individuals wishing to build customized recommender systems for their apps and implement machine/deep learning algorithms; individuals passionate about content and collaborative filtering-based and two tower-based recommender systems. Machine and deep learning practitioners, research scholars, and data scientists would also benefit from this course. As prerequisites, no prior recommender systems, ML, data analysis knowledge is needed. Basic Python knowledge is required.

Approach

The course is designed to assist you in understanding concepts clearly, and provides a unique hands-on experience. This course is expressive and self-explanatory, to the point, and practical with live coding. This straightforward learning-by-doing approach will help you in mastering the concepts and methodologies easily. This is a complete package with in-depth projects covering all course content.

Key Features

This complete package explores recommender system applications and machine/deep learning with Python * Learn to implement deep learning-based recommender systems and two-tower model implementation * Explore content-based concepts for an item-based recommender system with machine learning and Python

Github Repo

https://github.com/PacktPublishing/Recommender-Systems-Complete-Course-Beginner-to-Advance

About the Author

AI Sciences

AI Sciences are experts, PhDs, and artificial intelligence practitioners, including computer science, machine learning, and Statistics. Some work in big companies such as Amazon, Google, Facebook, Microsoft, KPMG, BCG, and IBM. AI sciences produce a series of courses dedicated to beginners and newcomers on techniques and methods of machine learning, statistics, artificial intelligence, and data science. They aim to help those who wish to understand techniques more easily and start with less theory and less extended reading. Today, they publish more comprehensive courses on specific topics for wider audiences. Their courses have successfully helped more than 100,000 students master AI and data science.

Course Outline

1. Introduction

This section focuses on introducing the author of the course, the course contents in general, and what you will learn from the course. It also briefly outlines recommender systems, including machine learning and deep learning.

1. Module and Instructor Introduction

This video introduces the author/instructor and the module's contents in general.

2. AI Sciences

This video briefly introduces the authors of the course, AI Sciences, and what kinds of courses it delivers worldwide.

3. Course Outline

This general introduction to the course outlines what you will learn regarding recommender systems and their components.

4. Machine Learning Recommender Systems

This video outlines the machine learning-based recommender system with the help of Python.

5. Deep Learning Recommender Systems

In this video, we will understand deep learning-based recommender systems with the aid of Python.

2. Recommender Systems with Machine Learning

This section focuses on recommender systems and machine learning, process and goals, recommender system generations, applications, and real-world challenges.

1. Motivation for Recommender System: Recommender Systems Overview

This video presents a brief overview of recommender systems, how they work, the processes and goals of a recommender system, and the pros and cons.

2. Motivation for Recommender System: Introduction to Recommender Systems

This video illustrates the recommender system's popularity based on demand. We will also look at the reasons for the recommender system boost.

3. Motivation for Recommender System: Recommender Systems Process and Goals

In this video, we will understand the need for recommender systems and the processes and goals involved.

4. Motivation for Recommender System: Generations of Recommender Systems

In this lesson, we will look at the first, second, and third generations of recommender systems.

5. Motivation for Recommender System: Nexus of AI and Recommender Systems

In this video, we will understand the nexus between artificial intelligence and recommender systems.

6. Motivation for Recommender System: Applications and Real-World Challenges

Here, you will learn about the real-world challenges faced by recommender systems.

7. Motivation for Recommender System: Quiz

This video is a quiz based on the learnings of the lectures and concepts so far.

8. Motivation for Recommender System: Quiz Solution

This video is the solution to the quiz based on the learnings of the lectures and concepts so far.

9. Basics of Recommender System: Overview

In this video, you will learn about the taxonomy of recommender systems and use the recommender systems to get appropriate results.

10. Basics of Recommender System: Taxonomy of Recommender Systems

In this lecture, we will discuss the taxonomy of recommender systems, the personalized and non-personalized recommender systems.

11. Basics of Recommender System: ICM

In this lesson, you will learn about the item-context matrix, a list of items and attributes in the recommender system.

12. Basics of Recommender System: User Rating Matrix

In this video, we will understand what a user rating matrix is and how we can build a user rating matrix.

13. Basics of Recommender System: Quality of Recommender System

In this lesson, we will look at the quality of recommender systems through inferred preferences and ways to collect user opinions.

14. Basics of Recommender System: Online Evaluation Techniques

In this video, you will learn about the evaluation technique and focus on the online evaluation technique in this lecture.

15. Basics of Recommender System: Offline Evaluation Techniques

In this video, you will learn about the evaluation technique and focus on the offline evaluation technique in this lecture.

16. Basics of Recommender System: Data Partitioning

Here, we will look at data partitioning, represented as a URL.

17. Basics of Recommender System: Important Parameters

In this video, we will look at the important parameters defined in a recommender system.

18. Basics of Recommender System: Error Metric Computation

In this video, we will look at some of the metrics used to measure a recommender system's quality.

19. Basics of Recommender System: Content-Based Filtering

In this lesson, we will understand the first model of filtering, content-based filtering, and learn its pros and cons.

20. Basics of Recommender System: Collaborative Filtering and User-Based Collaborative Filtering

In this lesson, you will learn about collaborative filtering and user-based collaborative filtering.

21. Basics of Recommender System: Item Model and Memory-Based Collaborative Filtering

In this video, we will understand another collaborative filtering model, the item-based model.

22. Basics of Recommender System: Quiz

This video is a quiz based on the learnings of the lectures and concepts so far.

23. Basics of Recommender System: Quiz Solution

This video is the solutions for the quiz based on the learnings of the lectures and concepts so far.

24. Machine Learning for Recommender Systems: Overview

This video provides a brief outline of machine learning in recommender systems and how machine learning helps us adopt multiple types of recommender systems.

25. Machine Learning for Recommender Systems: Benefits of Machine Learning

Let's understand what role machine learning plays in a recommender system and what are the benefits of machine learning.

26. Machine Learning for Recommender Systems: Guidelines for ML

In this video, we will discuss a few guidelines for machine learning-based recommender systems.

27. Machine Learning for Recommender Systems: Design Approaches for ML

In this lecture, we will explore the design approaches for recommender systems using machine learning.

28. Machine Learning for Recommender Systems: Content-Based Filtering

In this lesson, we will understand content-based filtering and how to develop it with machine learning.

29. Machine Learning for Recommender Systems: Data Preparation for Content-Based Filtering

In this lesson, you will learn to develop content-based filtering for a recommender system using Python.

30. Machine Learning for Recommender Systems: Data Manipulation for Content-Based Filtering

In this lesson, you will learn how to extract information from our dataset.

31. Machine Learning for Recommender Systems: Exploring Genres in Content-Based Filtering

After learning to explore genres, we will look at term frequency and inverse document frequency.

32. Machine Learning for Recommender Systems: tf-idf Matrix

In this video, you will learn to make the recommendation engine using the tf-idf matrix.

33. Machine Learning for Recommender Systems: Recommendation Engine

In this lesson, we will begin making the recommendation engine and train the model to make recommendations.

34. Machine Learning for Recommender Systems: Making Recommendations

In this video, we will understand how to make a recommendation after creating the recommendation engine.

35. Machine Learning for Recommender Systems: Item-Based Collaborative Filtering

In this video, you will learn to use machine learning to develop item-based collaborative filtering.

36. Machine Learning for Recommender Systems: Item-Based Filtering Data Preparation

In this video, you will learn to implement Python to develop item-based collaborative filtering using Pandas, NumPy, and Matplotlib.

37. Machine Learning for Recommender Systems: Age Distribution for Users

In this video, we will develop a histogram to visualize the age distribution for users.

38. Machine Learning for Recommender Systems: Collaborative Filtering using KNN

This video demonstrates implementing a collaborative filter using the k-nearest neighbor algorithm.

39. Machine Learning for Recommender Systems: Geographic Filtering

In this lesson, you will learn how to filter users in a recommendation system based on a geographical region.

40. Machine Learning for Recommender Systems: KNN Implementation

In this lesson, you will learn how to implement the k-nearest neighbor algorithm in machine learning.

41. Machine Learning for Recommender Systems: Making Recommendations with Collaborative Filtering

In this lesson, you will learn to implement recommendations with collaborative filtering.

42. Machine Learning for Recommender Systems: User-Based Collaborative Filtering

In this lesson, we will discuss user-based collaborative filtering in machine learning for a recommender system.

43. Machine Learning for Recommender Systems: Quiz

This video is a quiz based on the learnings of the lectures and concepts so far.

44. Machine Learning for Recommender Systems: Quiz Solution

This video is the solution to the quiz based on the learnings of the lectures and concepts so far.

45. Project 1: Song Recommendation System Using Content-Based Filtering: Project Introduction

This video provides a brief overview of the content-based recommender system for songs.

46. Project 1: Song Recommendation System Using Content-Based Filtering: Dataset Usage

In this lesson, you will learn to develop our content-based filtering for the song project.

47. Project 1: Song Recommendation System Using Content-Based Filtering: Missing Values

In this lesson, we will develop a new data frame for our content-based filtering for missing values.

48. Project 1: Song Recommendation System Using Content-Based Filtering: Exploring Genres

In this lesson, we will explore the elements of the dataset called genres.

49. Project 1: Song Recommendation System Using Content-Based Filtering: Occurrence Count

In this video, you will learn how to count the number of occurrences of each element in content-based filtering.

50. Project 1: Song Recommendation System Using Content-Based Filtering: tf-idf Implementation

In this video, we will understand how to calculate and use the tf-idf vectorizers with sklearn.

51. Project 1: Song Recommendation System Using Content-Based Filtering: Similarity Index

In this lesson, we will explore how to use the similarity index.

52. Project 1: Song Recommendation System Using Content-Based Filtering: Fuzzywuzzy Implementation

You will learn to develop the two types of functions needed to make the recommender engine.

53. Project 1: Song Recommendation System Using Content-Based Filtering: Find Closest Title

In this lesson, we will try to locate the nearest element to the search, and we will do this using functions.

54. Project 1: Song Recommendation System Using Content-Based Filtering: Making Recommendations

This is the final part of the project, where we create functions for the content-based recommender.

55. Project 2: Movie Recommendation System Using Collaborative Filtering: Project Introduction

This video provides an overview of the movie recommendation system using collaborative filtering.

56. Project 2: Movie Recommendation System Using Collaborative Filtering: Dataset Discussion

In this video, we will look at the various libraries we would need to import for this project, including os, math, NumPy, time, and Pandas.

57. Project 2: Movie Recommendation System Using Collaborative Filtering: Rating Plot

In this video, you will learn to perform data visualization and analysis for the project using the movies and ratings dataset.

58. Project 2: Movie Recommendation System Using Collaborative Filtering: Count

In this lesson, we will create functions to calculate the count of the elements of the project.

59. Project 2: Movie Recommendation System Using Collaborative Filtering: Logarithm of Count

In this video, we will explore how to calculate the count of elements using the logarithm function.

60. Project 2: Movie Recommendation System Using Collaborative Filtering: Active Users and Popular Movies

In this video, we will understand how to calculate our movie project's active users and popular movies.

61. Project 2: Movie Recommendation System Using Collaborative Filtering: Create Collaborative Filter

In this lesson, you will learn how to create a collaborative filter for the movie recommender system.

62. Project 2: Movie Recommendation System Using Collaborative Filtering: KNN Implementation

Here, you will learn how to implement the k-nearest neighbor algorithm in the movie recommender system.

63. Project 2: Movie Recommendation System Using Collaborative Filtering: Making Recommendations

We will explore how to make recommendations using collaborative filtering in the movie recommender system.

3. Deep Learning for Recommender Systems: An Applied Approach

This section focuses on deep learning for recommender systems, including inference, embeddings, user context, neural collaborative filtering, deep learning strengths and weaknesses, the TensorFlow recommender, and the two-tower model for recommender systems.

1. Deep Learning Foundation for Recommender Systems: Module Introduction

This video briefly introduces deep learning concepts for recommender systems and outlines the concepts to be covered in this module.

2. Deep Learning Foundation for Recommender Systems: Overview

This is a more detailed overview of the deep learning methodology in recommender systems. We will look at the benefits of using deep learning in recommender systems.

3. Deep Learning Foundation for Recommender Systems: Deep Learning in Recommendation systems

As we are aware, recommender systems are migrating from machine learning to deep learning, the reason being to capture non-linear and non-trivial relationships.

4. Deep Learning Foundation for Recommender Systems: Inference After Training

In this video, you will learn about the inference mechanisms for generic recommender systems, including training the system to capture information to make recommendations.

5. Deep Learning Foundation for Recommender Systems: Inference Mechanism

In this video, you will learn about the inference mechanisms for generic recommender systems, including individual interests, candidate generation, ranking and filtering, and item similarities.

6. Deep Learning Foundation for Recommender Systems: Embeddings and User Context

In this video, we will discuss deep neural network models that are built on the technique of factorization, and interactions between variables and embeddings are taken into account.

7. Deep Learning Foundation for Recommender Systems: Neural Collaborative Filtering

In this video, you will learn about another deep learning filter called neural collaborative filtering that uses latent and item latent vectors.

8. Deep Learning Foundation for Recommender Systems: VAE Collaborative Filtering

Let's understand the variational autoencoder for collaborative filtering using a representation obtained in the hidden layers.

9. Deep Learning Foundation for Recommender Systems: Strengths and Weaknesses of DL Models

This video discusses in detail the strengths and weaknesses of deep learning models, including non-linear transformations and non-trivial relationships.

10. Deep Learning Foundation for Recommender Systems: Deep Learning Quiz

This video is a quiz based on the learnings of the lectures and concepts so far.

11. Deep Learning Foundation for Recommender Systems: Deep Learning Quiz Solution

This video is the solution to the quiz based on the learnings of the lectures and concepts so far.

12. Project Amazon Product Recommendation System: Module Overview

In this video, we will look at another project based on a product recommendation using a library called TensorFlow with an Amazon dataset.

13. Project Amazon Product Recommendation System: TensorFlow Recommenders

This video briefly overviews the TensorFlow recommender, an open-source library for building recommender systems.

14. Project Amazon Product Recommendation System: Two-Tower Model

This lecture elaborates on the two-tower model, which we have already seen in the previous projects and modules of the course.

15. Project Amazon Product Recommendation System: Project Overview

This video briefly outlines the project and demonstrates the packages installation for the project, TensorFlow, data preparation, recommender development, and testing.

16. Project Amazon Product Recommendation System: Download Libraries

Here, you will learn to implement the Amazon product recommendation system using deep learning. We will import the requisite libraries and build and train the deep learning-based model using TensorFlow.

17. Project Amazon Product Recommendation System: Data Visualization with WordCloud

In this video, we will explore how to load the dataset and begin data visualization using WordCloud.

18. Project Amazon Product Recommendation System: Make Tensors from DataFrame

We will now advance further by checking our dataset using a single user and developing the Tensor from DataFrame.

19. Project Amazon Product Recommendation System: Rating Our Data

Let us now move to the next part of the project, including the rating of our data with a new mapping dictionary.

20. Project Amazon Product Recommendation System: Random Train-Test Split

After mapping the rating to the dataset, we will train-test split the dataset to our recommender system with shuffling and prediction.

21. Project Amazon Product Recommendation System: Making the Model and Query Tower

After testing and training the recommendations, we will develop the model by loading the Tensor board extension.

22. Project Amazon Product Recommendation System: Candidate Tower and Retrieval System

In this lesson, we will look at making the candidate tower and then execute a retrieval system.

23. Project Amazon Product Recommendation System: Compute Loss

This is the next step of training our model, which entails the compute loss model.

24. Project Amazon Product Recommendation System: Train and Validation

After entirely developing our recommender system, we will perform the training and validation, fitting and evaluating our model.

25. Project Amazon Product Recommendation System: Accuracy Versus Recommendations

We will now perform data visualization; we will check the accuracy of our recommender model with the recommendations.

26. Project Amazon Product Recommendation System: Making Recommendations

We will now perform some recommendations using the brute-force algorithms and then perform the indexing of our data.

Course Images

Recommender Systems Complete Course Beginner to Advanced

By Packt

Booking options

Highlights

Description

Course Content

About The Provider

Tags

Reviews