Data-driven impact assessment of multidimensional project complexity on project performance

Abstract

Purpose

The purpose of this paper is to propose a data-driven scheme for identifying critical project complexity dimensions and establishing the trade-off across multiple project performance criteria.

Design/methodology/approach

This paper adopts a hybrid approach using Bayesian Belief Networks (BBNs) and Artificial Neural Networks (ANNs). The output of the ANN model is used as input to the BBN model for prioritizing project complexity dimensions relative to multiple project performance criteria. The proposed process is demonstrated through a real application in the construction industry.

Findings

With a number of nonlinear interactions involved within and across project complexity and performance, it is not feasible to model and assess the strength of these interactions using conventional techniques. The proposed process helps in effectively mapping a “multidimensional complexity” space to a “multidimensional performance” space and makes use of data from past projects for operationalizing this mapping scheme by means of ANNs. This obviates the need for developing a parametric model that is both challenging and computationally cumbersome. The mapping function can be used for generating all possible scenarios required for the development of a data-driven BBN model.

Originality/value

This paper introduces a data-driven process for operationalizing the mapping of project complexity to project performance within a network setting of interacting complexity dimensions and performance criteria. The results of the application study manifest the importance of capturing the interdependency across project complexity and performance. Ignoring the underlying interdependencies and relying exclusively on conventional correlation-based techniques may lead to making suboptimal decisions.

Citation

Qazi, A. (2022), "Data-driven impact assessment of multidimensional project complexity on project performance", International Journal of Productivity and Performance Management, Vol. 71 No. 1, pp. 58-78. https://doi.org/10.1108/IJPPM-06-2020-0281