Aggregating diverse evaluations in group decision making: An approach based on wisdom of crowds

Abstract

Group decision-making (GDM) requires individuals to weigh and aggregate individual evaluations. Diverse evaluations within a group usually require a consensus reaching process (CRP). However, CRP does not aim to improve group evaluation accuracy. The wisdom of crowds (WOC) applies statistical aggregations to obtain group predictions, without necessitating a certain degree of group consensus. Current WOC techniques identify individual expertise levels based on real outcomes of events, or individuals' meta-information, which might not be obtainable in GDM problems. This study proposes an approach for GDM problems with diverse evaluations provided by individuals with different expertise levels. It weighs individuals based on their contributions to the group, by estimating the evaluated attributes' real outcomes and updating individual weights within a time series. The approach is verified by real collected data and simulated data, then compared with several similar weighting methods and CRP techniques. The results demonstrate the approach's good performance in large groups, with improved identification of expertise levels in diverse groups, without requiring a large number of time points in the time-series.