deep_ncf: Deep Learning Recommendation: Neural Collaborative Filtering
In tianwei-zhang/easyAI: Democratize AI

Deep Learning Recommendation: Neural Collaborative Filtering

deep_ncf(data, num_layer = seq(1, 5, 1), max_units = 10, start_unit = 3,
  max_lr = 0.2, min_lr = 0.001, iteration_per_layer = 5,
  min_mf_output_dim = 2, max_mf_output_dim = 10, num_epoch = 2,
  top = 100)

`data`	Transaction dataset. Format must be order_id (could be dummy), user_id, and product_id
`num_layer`	a vector of integers indicating the number of hidden layers to test. Default to seq(1,5,1)
`max_units`	the maximum number of hidden units in a layer. Default to 10
`start_unit`	the minimum number of hiddent units in a layer. Default to 3
`max_lr`	maximum learning rate in a run. Default to 0.2
`min_lr`	minimum learning rate in a run. Default to 0.001
`iteration_per_layer`	Number of parameter randomizations for a given number of hidden layers. More iterations will explore a larger parameter space
`min_mf_output_dim`	Min number of latent factors to represent users and items
`max_mf_output_dim`	Max number of latent factors to represent users and items
`num_epoch`	number of epoches to go through during training
`top`	Number of top products and customers to include. Can be NULL (e.g. will include everything)

returns a list object with two values: train_performance: A table with parameters and model performance metrics best_model: a keras_model object with the optimal parameters

tianwei-zhang/easyAI documentation built on May 14, 2019, 12:48 p.m.