Abstract

paper/sl.tex

@@ -102,18 +102,19 @@ Second, the past decision in the data may skew the data, and, in particular, any
 %
 For example, when a bank decides whether a customer should be granted a loan, it is desired to grant loans to customers who would honor its conditions, but not to ones who would violate them.
 %
-However, we can directly evaluate only the decision to grant the loan, while we cannot observe whether customers who were not granted the loan would indeed violate its conditions. 
+However, we can directly observe outcomes only for the decisions to grant the loan, while we cannot observe whether customers who were not granted the loan would indeed violate its conditions. 
 %
 %THIS IS NOT SKEW THIS IS MISSING DATA
 % 
-Such bias appears in the decisions of both human and AI decision makers -- and should be properly taken into account for evaluation.
+Such difficulties appear in the recorded decisions of both human and AI decision makers -- and should be properly taken into account for evaluation.
 %
 %Further complications arise since commonly not all features that the decisions are based on are observed. DISCUSS UNOBSERVABLES IN THE INTRO?
 %
 In this paper, we develop a Bayesian approach towards this end.
 %
-We use a detailed causal model of the decision making process, taking into account also unobserved features.
-Based on this model, we evaluate counterfactual outcomes to correct any aforementioned biases. 
+We use a proper causal model of the decision making process, taking into account also the unobserved features.
+Based on this model, we compute counterfactual outcomes, which in turn allow us to produce accurate evaluations of decision maker policies.
+ %to correct any aforementioned biases. 
  % to infer unobserved outcomes.
 %
 Compared to previous methods for this setting, the approach estimates the quality of decisions more accurately and with lower variance.