•  
  •  
 

Abstract

This Article examines a prominent idea in the law and technology literature: that algorithms and big data can be used to make law dynamic and personalized. As currently envisioned by legal scholars, “algorithmic law” entails laws that adjust in real time to changing conditions and vary across individuals, improving welfare by tailoring legal rules and standards to personal characteristics.

This Article argues that this vision of algorithmic law is incomplete—and often counterproductive. Existing proposals treat personalization as a function of individual attributes alone, overlooking the fact that effects of individual behavior are fundamentally interactive. Individual behavior is shaped by spatial spillovers, social norms, enforcement costs, externalities, and feedback effects in complex systems. As a result, optimizing the law at the level of isolated individuals does not always produce welfare gains at the aggregate level, and may fail even on its own terms. Urban mobility provides illustrative examples of how personalized algorithmic law can misfire when interactive effects are ignored. These examples suggest that the central challenge of algorithmic law is not simply personalization, but coordination.

To address this problem, the Article proposes an alternative method for designing algorithmic law that treats all activity as interdependent. Rather than generating separate laws for each individual, lawmakers would construct coordinated sets of laws applied simultaneously across populations, designed to account for spatial and social interactions and to maximize social welfare system-wide. Properly accounting for interaction effects often leads not to greater legal differentiation, but to renewed justification for uniform laws in many settings.

Share

COinS