Applied Recommender Systems with Python : Build Recommender Systems with Deep Learning, NLP and Graph-Based Techniques / Akshay Kulkarni, Adarsha Shivananda, Anoosh Kulkarni, V Adithya Krishnan.

Intro
Table of Contents
About the Authors
About the Technical Reviewer
Preface
Chapter 1: Introduction to Recommendation Systems
What Are Recommendation Engines?
Recommendation System Types
Types of Recommendation Engines
Market Basket Analysis (Association Rule Mining)
Content-Based Filtering
Collaborative-Based Filtering
Hybrid Systems
ML Clustering
ML Classification
Deep Learning
Rule-Based Recommendation Systems
Popularity
Global Popular Items
Popular Items by Country
Buy Again
Summary

Chapter 2: Market Basket Analysis (Association Rule Mining)
Implementation
Data Collection
Importing the Data as a DataFrame (pandas)
Cleaning the Data
Insights from the Dataset
Customer Insights
Loyal Customers
Number of Orders per Customer
Money Spent per Customer
Patterns Based on DateTime
Preprocessing the Data
How Many Orders Are Placed per Month?
How Many Orders Are Placed per Day?
How Many Orders Are Placed per Hour?
Free Items and Sales
Item Insights
Most Sold Items Based on Quantity
Items Bought by the Highest Number of Customers

Most Frequently Ordered Items
Top Ten First Choices
Frequently Bought Together (MBA)
Apriori Algorithm Concepts
Association Rules
Implementation Using mlxtend
If A => then B
Creating a Function
Validation
Visualization of Association Rules
Summary
Chapter 3: Content-Based Recommender Systems
Approach
Implementation
Data Collection and Downloading Word Embeddings
Importing the Data as a DataFrame (pandas)
Preprocessing the Data
Text to Features
One-Hot Encoding (OHE)
CountVectorizer
Term Frequency-Inverse Document Frequency (TF-IDF)

Word Embeddings
Similarity Measures
Euclidean Distance
Cosine Similarity
Manhattan Distance
Build a Model Using CountVectorizer
Build a Model Using TF-IDF Features
Build a Model Using Word2vec Features
Build a Model Using fastText Features
Build a Model Using GloVe Features
Build a Model Using a Co-occurrence Matrix
Summary
Chapter 4: Collaborative Filtering
Implementation
Data Collection
About the Dataset
Memory-Based Approach
User-to-User Collaborative Filtering
Implementation
Item-to-Item Collaborative Filtering
Implementation

KNN-based Approach
Machine Learning
Supervised Learning
Unsupervised Learning
Reinforcement Learning
Supervised Learning
Regression
Classification
K-Nearest Neighbor
Implementation
Summary
Chapter 5: Collaborative Filtering Using Matrix Factorization, Singular Value Decomposition, and Co-Clustering
Implementation
Matrix Factorization, Co-Clustering, and SVD
Implementing NMF
Implementing Co-Clustering
Implementing SVD
Getting the Recommendations
Summary
Chapter 6: Hybrid Recommender Systems
Implementation
Data Collection
Data Preparation