Continual learning with a Bayesian approach for evolving the baselines of a leagile project portfolio

Abstract

This article introduces a Bayesian learning approach for planning continuously evolving leagile project and portfolio baselines. Unlike the traditional project management approach, which uses static project baselines, the approach proposed in this study suggests learning from immediately prior experience to establish an evolving baseline for performance estimation. The principle of Pasteur’s quadrant is used to realize a highly practical solution, which extends the existing wisdom on leagile continuous planning. This study compares the accuracy of the proposed Bayesian approach with the traditional approach using real data. The results suggest that the evolving Bayesian baselines can generate a more realistic measure of performance than traditional baselines, enabling leagile projects and portfolios to be better managed in the continuously changing environments of today.