Related skills · check the marketing fit
Implement collaborative filtering, matrix factorization, neural models and ranking using NumPy/Keras/TensorFlow/Spark, broad technical recommender course is adjacent to personalization marketing
Lazy Programmer Inc. , Lazy Programmer Team · Udemy
Implement collaborative filtering, matrix factorization, neural models and ranking using NumPy/Keras/TensorFlow/Spark. Broad technical recommender course is adjacent to personalization marketing
Selected published requirements: “For advanced sections, know calculus, linear algebra, and probability for a deeper understanding”. See the provider page for the full requirements and current tool terms
Practice: A collaborative-filtering exercise uses the MovieLens 20M data to build a similarity-based predictor and compare training and test error. A matrix-factorization exercise prompt is also listed
Recorded Udemy course advertised with a public course preview. Exact lesson count may be unknown. Purchase or organization-subscription terms and current availability require checking
Related tasks, tools and formats. Check the differences before choosing.
Sundog Education by Frank Kane , Frank Kane , Sundog Education Team
Build and evaluate content/collaborative, matrix-factorization, neural and session-based recommenders, with Netflix/YouTube examples and production-scale methods. Technical recommendation training transfers to customer content/product…
Mammoth Interactive , John Bura
Build a positive/negative review classifier in a ten-lesson/79-minute project after Python/NumPy/pandas/ML/TensorFlow foundations, the whole course counts once and is adjacent technical training
Minerva Singh
Implement content-based, collaborative and hybrid recommendation approaches in R and relate user-item preference predictions to e-commerce personalization