Supervised Machine Learning Methods for Item Recommendation

class, 107accuracy, 40AdaBoost, 77adaptivity, 41age, 81ALS, see alternating least squaresalternating least squares, 36, 86Apache Mahout, 86area under the ROC curve, 41, 61, 82aspect model, 58association rules, 87attribute-based kNN, 81attribute-to-factor mapping, 45 59AUC, see area under the ROC curve bagging, 77, 87Bayesian Context-Aware Ranking, 38Bayesian Personalized Ranking, 38 39,61 66, 82binary classi cation, 62BPR, see Bayesian Personalized Rank-ingBPR-MF, 39, 81 C, 92C++, 80, 92C#, 88, 92, 122case-based reasoning, 87categories, 81chronological splits, 82classi cation, 24, 27, 61clustering, 24, 87co-clustering, 80COFI, 87Co Rank, 38, 88cold-start problem, 45 59collaborative ltering, 61command-line tools, 81competitive collaborative ltering, 29computer vision, 79con dence, 40conjugate gradient, 36content-based ltering, 88context, 26context-aware recommendation, 29, 89contextual modeling, 40contextual postltering, 40contextual preltering, 40cosine similarity, 34cost-sensitive learning, 63coverage, 40Crab, 87cross-validation, 83 decision trees, 35demographic data, 81dense matrix, 108diagonal, 84distributed matrix factorization, 83diversity, 41documentation, 84dot product, 45Duine, 88, 92 e-commerce, 27e-LICO, 96EasyRec, 87Eigentaste, 87EM, see expectation-maximizationensemble, 70, 87, 122epoch, 35evaluation, 40, 51, 82, 93expectation-maximization, 36explicit context, 29explicit feedback, 25 F#, 80, 123Facebook, 28