NECTAR : Game-Theoretic Factory Inspection Scheduling and Explanation for Toxic Wastewater Abatement ∗

Leather is an integral part of the world economy and a substantial income source for developing countries. Despite government regulations on leather tannery waste emissions, inspection agencies lack adequate enforcement resources, and tanneries’ toxic wastewaters wreak havoc on surrounding ecosystems and communities. Previous works in this domain stop short of generating executable solutions for inspection agencies. We introduce NECTAR the first security game application to generate environmental compliance inspection schedules. NECTAR’s game model addresses many important real-world constraints: a lack of defender resources is alleviated via a secondary inspection type; imperfect inspectors are modeled via a heterogeneous failure rate; and uncertainty, in traveling through a road network and in conducting inspections, is addressed via a Markov Decision Process. Previously unexplored in security game literature, NECTAR features a novel explanation system to improve user understanding of inspection schedules; understandability is a critical component to build trust and facilitate user adoption. This explanation system generalizes to any security game type, and we demonstrate its application to NECTAR. To evaluate our model, we conduct a series of simulations and analyze their policy implications. We also conduct a preliminary survey to assess explanation systems’ potential impact on understandability.