Building a Machine Learning Recommendation System
Chapter 1: Foundations of Recommendation Systems
What are Recommendation Systems?
Taxonomy of Recommender Engines
Understanding User-Item Interaction Data
Implicit vs. Explicit Feedback
The Cold-Start Problem
Preparing Your Development Environment
Practice: Loading and Inspecting a Dataset
Chapter 2: Content-Based Filtering
The Mechanics of Content-Based Recommenders
Creating Item Profiles from Metadata
Vectorizing Text Data with TF-IDF
Computing Similarity with Cosine Distance
Generating User Profiles
Producing Content-Based Recommendations
Hands-on Practical: Building a Movie Recommender
Chapter 3: Neighborhood-Based Collaborative Filtering
The Rationale Behind Collaborative Filtering
The User-Item Interaction Matrix
User-Based vs. Item-Based Approaches
Finding Similar Users and Items with k-Nearest Neighbors
Calculating Similarity Metrics
Making Predictions with Weighted Averages
Addressing Sparsity in the Interaction Matrix
Hands-on Practical: Implementing an Item-Based Filter
Chapter 4: Model-Based Collaborative Filtering with Matrix Factorization
From Neighborhoods to Latent Factor Models
Introduction to Matrix Factorization
Singular Value Decomposition (SVD) for Recommendations
Optimization with Stochastic Gradient Descent (SGD)
Regularization to Prevent Overfitting
Using Libraries for Matrix Factorization
Hands-on Practical: Generating Recommendations with SVD
Chapter 5: Evaluating Recommendation Systems
The Importance of Recommender Evaluation
Offline vs. Online Evaluation Methods
Splitting Data for Recommender Evaluation
Prediction Accuracy Metrics: RMSE and MAE
Ranking Metrics: Precision and Recall at K
Mean Average Precision (MAP)
Normalized Discounted Cumulative Gain (NDCG)
Hands-on Practical: Measuring Model Performance
Chapter 6: Constructing a Hybrid Recommendation System
Limitations of Single-Algorithm Systems
Combining Recommender Models
Weighted Hybridization
Switching and Mixed Hybridization Techniques
Feature Combination Methods
Building a System that Blends Content and Collaborative Signals
Hands-on Practical: A Weighted Hybrid Movie Recommender
Normalized Discounted Cumulative Gain (NDCG)
Was this section helpful?
- Cumulated gain-based evaluation of IR techniques, Kalervo Järvelin, Jaana Kekäläinen, 2002 ACM Transactions on Information Systems (TOIS), Vol. 20 (ACM) DOI: 10.1145/582415.582418 - This paper introduces Discounted Cumulative Gain (DCG) and Normalized Discounted Cumulative Gain (NDCG) as key metrics for evaluating information retrieval systems, laying the groundwork for their widespread adoption.
- Introduction to Information Retrieval, C.D. Manning, P. Raghavan, H. Schütze, 2008 (Cambridge University Press) - A classic textbook in information retrieval, providing a thorough explanation of ranking evaluation metrics, including NDCG, within the context of search and relevance assessment. Chapter 8 is particularly relevant.
- Recommender Systems: An Introduction, Dietmar Jannach, Markus Zanker, Alexander Felfernig, Gerhard Friedrich, 2010 (Cambridge University Press) - This textbook offers an accessible introduction to the field of recommender systems, dedicating a section to evaluation metrics where NDCG is discussed in the context of recommendation quality.
- Recommender Systems Handbook, Francesco Ricci, Lior Rokach, Bracha Shapira, 2022 (Springer US) DOI: 10.1007/978-1-0716-2197-4 - A comprehensive handbook on recommender systems, featuring contributions from leading researchers. It provides extensive coverage of evaluation methodologies and metrics, including NDCG, for assessing system performance.