summarize_segments: Summarize CATE Estimates and Dynamic Treatment Rule Across...
In Netflix/sherlock: Causal Machine Learning for Segment Discovery and Analysis

Produce a summary of the segments and the segment-specific treatment rule assignment based on estimates of the conditional average treatment effect (CATE) within each segment. When the dynamic treatment rule has not yet been assigned via assign_rule, just segment specific summaries of the CATE estimates and their standard error are returned.

1	summarize_segments(data_with_rule)

data_with_rule

A data.table containing the input data, augmented with cross-validated nuisance parameter estimates, an estimate of the CATE, and a treatment rule assigned based on the estimated CATE via assign_rule. This input object should be created by successive calls to set_est_data, est_cate, and assign_rule in a sequence, or through a wrapper function that composes these function calls automatically. When assign_rule has not been called, summary of the rule assignment and relevant evaluation of the CATE is skipped and only segment-specific CATE summaries are output.

A data.table containing the discovered segments, the estimated CATE within each segment (with inference for the CATE), the segment-specific treatment rule assignment, and auxiliary info for assessing the quality of the segmentation.

Netflix/sherlock documentation built on Dec. 17, 2021, 5:22 a.m.