Inducing and Mitigating a Self-Reinforcing Degradation in Decision-making Teams

TL;DR

This paper analyzes how positive feedback can cause overload and collapse in decision-making organizations, and proposes strategies to mitigate such self-reinforcing degradation through dynamic decision responsibility allocation.

Contribution

It introduces a system-theoretic dynamic model of decision overload and proposes practical mitigation strategies for hierarchical organizations.

Findings

Overload propagates through hierarchical structures causing decision quality degradation.

Mitigation strategies include load dumping, empowering lower levels, and online diagnostics.

Dynamic allocation of decision responsibilities can improve organizational resilience.

Abstract

The models in this paper demonstrate how self-reinforcing error due to positive feedback can lead to overload and saturation of decision-making elements, and ultimately the cascading collapse of an organization due to the propagation of overload and erroneous decisions throughout the organization. We begin the paper with an analysis of the stability of the decision-making aspects of command organizations from a system-theoretic perspective. A simple dynamic model shows how an organization can enter into a self-reinforcing cycle of increasing decision workload until the demand for decisions exceeds the decision-making capacity of the organization. We then extend the model to more complex networked organizations and show that they also experience a form of self-reinforcing degradation. In particular, we find that the degradation in decision quality has a tendency to propagate through the hierarchical structure, i.e. overload at one location affects other locations by overloading the higher-level components which then in turn overload their subordinates. Our computational experiments suggest several strategies for mitigating this type of malfunction: dumping excessive load, empowering lower echelons, minimizing the need for coordination, using command-by-negation, insulating weak performers, and applying on-line diagnostics. We describe a method to allocate decision responsibility and arrange information flow dynamically within a team of decision-makers for command and control.