David Ríos Insua

Policy analysis and policy analytics

Working from a description of what policy analysis entails, we review the emergence of the recent field of analytics and how it may impact public policy making. In particular, we seek to expose current applications of, and future possibilities for, new analytic methods that can be used to support public policy problem-solving and decision processes, which we term policy analytics. We then review key contributions to this special volume, which seek to support policy making or delivery in the areas of energy planning, urban transportation planning, medical emergency planning, healthcare, social services, national security, defence, government finance allocation, understanding public opinion, and fire and police services. An identified challenge, which is specific to policy analytics, is to recognize that public sector applications must balance the need for robust and convincing analysis with the need for satisfying legitimate public expectations about transparency and opportunities for participation. This opens up a range of forms of analysis relevant to public policy distinct from those most common in business, including those that can support democratization and mediation of value conflicts within policy processes. We conclude by identifying some potential research and development issues for the emerging field of policy analytics.

An Adversarial Risk Analysis Model for an Autonomous Imperfect Decision Agent

Machines that perform intelligent tasks interacting with humans in a seamless manner are becoming a reality. A key element in their design is their ability to make decisions based on a reasonable value system, and the perception of the surrounding environment, including the incumbent persons. In this chapter, we provide a model that supports the decision making process of an autonomous agent that imperfectly perceives its environment and the actions performed by a person, which we shall designate user. The approach has a decision analytic flavour, but includes models forecasting the user’s behaviour and its impact over the surrounding environment. We describe the implementation of the model with an edutainment robot with sensors that capture information about the world around it, which may serve as a cognitive personal assistant, may be used with kids for educational, recreational and therapeutic purposes and with elderly people for companion purposes.

Risk Analysis for Unintentional Slide Deployment During Airline Operations

We present a risk analysis undertaken to mitigate problems in relation to the unintended deployment of slides under normal operations within a commercial airline. This type of incident entails relevant costs for the airline industry. After assessing the likelihood and severity of its consequences, we conclude that such risks need to be managed. We then evaluate the effectiveness of various countermeasures, describing and justifying the chosen ones. We also discuss several issues faced when implementing and communicating the proposed measures, thus fully illustrating the risk analysis process.

Security economics: an adversarial risk analysis approach to airport protection

We analyze the case of protecting an airport, in which there is concern with terrorist threats against the Air Traffic Control Tower. To deter terrorist actions, airport authorities rely on various protective measures, which entail multiple consequences. By deploying them, airport authorities expect to reduce the probabilities and potential impacts of terrorist actions. We aim at giving advice to the airport authorities by devising a security resource allocation plan. We use the framework of adversarial risk analysis to deal with the problem.

Critical networked infrastructure protection from adversaries

Abstract We use the adversarial risk analysis (ARA) framework to deal with the protection of a critical networked infrastructure from the attacks of intelligent adversaries. We deploy an ARA model for each relevant element (node, link, hotspot in link) in the network, using a Sequential Defend–Attack–Defend template as a reference. Such ARA models are related by resource constraints and result aggregation over various sites, for both the Defender and the Attacker. As a case study, we consider the protection of a section of the Spanish railway network from a potential terrorist attack.

Robustness for Adversarial Risk Analysis

Adversarial Risk Analysis is an emergent paradigm for supporting a decision maker who faces adversaries in problems in which the consequences are random and depend on the actions of all participating agents. In this chapter, we outline a framework for robust analysis methods in Adversarial Risk Analysis. Our discussion focuses on security applications.

Adversarial issues in reliability

Many reliability problems involve two or more agents with conflicting interests whose decisions affect the performance of the system at hand. Examples of such problems relevant in management practice abound and include acceptance sampling, life testing, software testing, optimal maintenance, reliability demonstration, warranties and insurance. Most earlier attempts in such problems have focused on game theoretic approaches based on Nash equilibria and related concepts. However, these require strong common knowledge assumptions which do not frequently hold in practice. We provide an alternative framework based on adversarial risk analysis to deal with such problems which avoids the strong common knowledge assumptions of game theory. We illustrate the framework through acceptance sampling and life testing problems.

GIRA: a general model for incident risk analysis

Abstract Most existing risk analysis methods focus on analysing risks that a system might face throughout its life. However, there is no explicit method for risk analysis during incidents. Approaches such as bow-ties and attack trees provide reliable information about triggers and escalation of incidents, but do not cover risk evaluation. Risk matrices include the entire risk analysis process; however, their risk evaluation approach is oversimplified. This paper presents a General Model for Incident Risk Analysis, which formalises the incident risk analysis process through an influence diagram. Our aim is to provide a decision support model that generates reliable risk information and enhances incident risk evaluation.

Adversarial Risk Analysis for Urban Security Resource Allocation.

Adversarial risk analysis (ARA) provides a framework to deal with risks originating from intentional actions of adversaries. We show how ARA may be used to allocate security resources in the protection of urban spaces. We take into account the spatial structure and consider both proactive and reactive measures, in that we aim at both trying to reduce criminality as well as recovering as best as possible from it, should it happen. We deal with the problem by deploying an ARA model over each spatial unit, coordinating the models through resource constraints, value aggregation, and proximity. We illustrate our approach with an example that uncovers several relevant policy issues.

Multithreat multisite protection: A security case study

We provide a novel adversarial risk analysis approach to security resource allocation decision processes for an organization which faces multiple threats over multiple sites. We deploy a Sequential Defend-Attack model for each type of threat and site, under the assumption that different attackers are uncoordinated, although cascading effects are contemplated. The models are related by resource constraints and results are aggregated over the sites for each participant and, for the Defender, by value aggregation across threats. We illustrate the model with a case study in which we support a railway operator in allocating resources to protect from two threats: fare evasion and pickpocketing. Results suggest considerable expected savings due to the proposed investments.