The Factorization Machines Algorithm has two modes: Classification and Regression. Classification is a binary method that returns either one or zero and a label which is a number. The Regression mode returns the predicted value. Factorization Machines are a good choice for high dimensional, sparse datasets. Common uses are web page click prediction and item recommendation.
For dense continuous data Linear Learner may be a better choice. However if you have sparse data with gaps and holes Factorisation Machines Algorithm may produce better results.
|Data types and format||Tabular|
|Learning paradigm or domain||Supervised Learning|
|Problem type||Binary classification, Regression|
|Use case examples||Predict a numeric/continuous value; Predict if an item belongs to a category|
For Factorization Machines Algorithm the training data has to be in x-recordio-protobuf format.
Model artifacts and inference
|Learning paradigm||Supervised Learning|
|Request format||JSON, x-recordio-protobuf|
Training can be done on CPU and GPU instances and distributed processing is supported. CPU instances are recommended for sparse data and GPU for dense data.
AWS Partner Webinar: Object2Vec on Amazon SageMaker
This is a 50.57 minutes video from AWS. It includes Factorization Machines and Object2Vec.