Model Details and Parameters

  • Updated

simMachines’ analytic engines are known as models. Each model is designed to solve a different type of problem. Several respond to queries in formats specific to the model and others show useful information about the data. This chapter covers the capacities and requirements of each model.

simMachines’ models are:

simSearch - Similarity Engine - Finds the objects in a dataset most similar to the queried object.

simClassify - Classification Engine - Uses a preselected distance function to identify the most similar objects in a dataset to classify / make a prediction on the queried object.

simClassify+ - Metric Learning Classification Engine - Produces a custom distance function and to identify the most similar objects in a dataset to classify / make a prediction on the queried object.

simRecommend - Recommendation Engine - Makes item recommendations for the queried individual based on other individuals in the dataset with similar preferences.

simCluster - Clustering Tool - Provides a way to visualize the groups of objects in a dataset. Clustering is agglomerative.

simCluster+ - Clustering Tool - Provides a way to visualize the groups of objects in a dataset. Clustering is KMeans or Spilling KMeans.

Was this article helpful?

0 out of 0 found this helpful

Comments

0 comments

Please sign in to leave a comment.