Machine Learning with Apache Spark

  1. Collaborative Filtering and Recommendation Systems
    1. Introduction to Recommender Systems
      1. Recommendation System Types
        1. Content-Based Filtering
          1. Item Profiles
            1. User Profiles
              1. Similarity Computation
              2. Collaborative Filtering
                1. User-Based Collaborative Filtering
                  1. Item-Based Collaborative Filtering
                    1. Memory-Based Approaches
                      1. Model-Based Approaches
                      2. Hybrid Approaches
                      3. Use Cases and Applications
                        1. E-commerce Recommendations
                          1. Content Recommendations
                            1. Social Network Recommendations
                            2. Evaluation Challenges
                              1. Rating Prediction vs Ranking
                                1. Cold Start Problems
                                  1. Data Sparsity Issues
                                2. Alternating Least Squares Algorithm
                                  1. Matrix Factorization Fundamentals
                                    1. User-Item Rating Matrix
                                      1. Latent Factor Models
                                        1. Low-Rank Matrix Approximation
                                        2. ALS Algorithm Details
                                          1. Alternating Optimization
                                            1. Least Squares Formulation
                                              1. Regularization Integration
                                              2. Explicit vs Implicit Feedback
                                                1. Rating-Based Systems
                                                  1. Implicit Feedback Interpretation
                                                    1. Confidence Weighting
                                                    2. Key Parameters
                                                      1. Rank (Number of Factors)
                                                        1. Regularization Parameter
                                                          1. Number of Iterations
                                                            1. Alpha Parameter for Implicit Feedback
                                                              1. Convergence Tolerance
                                                              2. Handling Cold Start Problem
                                                                1. New User Problem
                                                                  1. New Item Problem
                                                                    1. Mitigation Strategies
                                                                    2. Making Recommendations
                                                                      1. Rating Prediction
                                                                        1. Top-N Recommendation Generation
                                                                          1. Recommendation Filtering
                                                                            1. Diversity and Novelty Considerations

                                                                        Previous

                                                                        6. Unsupervised Learning with Spark ML

                                                                        Go to top

                                                                        Next

                                                                        8. Model Evaluation and Hyperparameter Tuning