Finance

Business

Social choice theory

Mathematics

Domain (mathematical analysis)

Knowledge management

Politics

Swap (finance)

Gene

Epistemology

Mathematical analysis

Philosophy

Political science

Dominance (genetics)

Artificial intelligence

Psychology

Economics

Microeconomics

Ethical dilemma

Chemistry

Social dilemma

Dilemma

Computer science

Management science

Preference

Voting

Biochemistry

Social psychology

We present a general approach to automating ethical decisions, drawing on machine learning and computational social choice. In a nutshell, we propose to learn a model of societal preferences, and, when faced with a specific ethical dilemma at runtime, efficiently aggregate those preferences to identify a desirable choice. We provide a concrete algorithm that instantiates our approach; some of its crucial steps are informed by a new theory of swap-dominance efficient voting rules. Finally, we implement and evaluate a system for ethical decision making in the autonomous vehicle domain, using preference data collected from 1.3 million people through the Moral Machine website.

A Voting-Based System for Ethical Decision Making