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; (iv) it does not necessitate network information of the target units. I introduce estimation procedures that leverage experimental or observational data and derive strong guarantees on the utilitarian regret. 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.