Policy Targeting under Network Interference

This paper discusses the problem of estimating treatment allocation rules under network interference. I propose a method with several attractive features for applications: (i) it does not rely on the correct specification of a particular structural model; (ii) it exploits heterogeneity in treatment effects for targeting individuals; (iii) it accommodates arbitrary constraints on the policy function, and (iv) it can also be implemented when network information is not accessible to policy-makers. I establish a set of guarantees on the utilitarian regret, i.e., the difference between the average social welfare attained by the estimated policy function and the maximum attainable welfare, allowing for known and unknown propensity score. I provide a mixed-integer linear program formulation, which can be solved using off-the-shelf algorithms. I illustrate the advantages of the method for targeting information on social networks.