Governance and Communication of Algorithmic Decision Making: A Case Study on Public Sector

TL;DR

This case study investigates how Dutch municipal governments use and govern Algorithmic Decision Making, highlighting the need for systematic frameworks, better communication, and oversight to improve public trust and effectiveness.

Contribution

The paper provides empirical insights into current ADM practices in municipalities and proposes actionable governance and communication strategies for public sector implementation.

Findings

Municipalities use ADM ad hoc without systematic processes.

There is a strong need for governance frameworks in ADM.

Communication on ADM is reactive to public and media scrutiny.

Abstract

Algorithmic Decision Making (ADM) has permeated all aspects of society. Government organizations are also affected by this trend. However, the use of ADM has been getting negative attention from the public, media, and interest groups. There is little to no actionable guidelines for government organizations to create positive impact through ADM. In this case study, we examined eight municipal organizations in the Netherlands regarding their actual and intended use of ADM. We interviewed key personnel and decision makers. Our results show that municipalities mostly use ADM in an ad hoc manner, and they have not systematically defined or institutionalized a data science process yet. They operate risk averse, and they clearly express the need for cooperation, guidance, and even supervision at the national level. Third parties, mostly commercial, are often involved in the ADM development lifecycle, without systematic governance. Communication on the use of ADM is generally responsive to negative attention from the media and public. There are strong indications for the need of an ADM governance framework. In this paper, we present our findings in detail, along with actionable insights on governance, communication, and performance evaluation of ADM systems.