Toggle Main Menu Toggle Search

Open Access padlockePrints

Insight from data analytics in a facilities management company

Lookup NU author(s): Dr Jaume Bacardit, Dr Shirley ColemanORCiD



This is the authors' accepted manuscript of an article that has been published in its final definitive form by John Wiley and Sons Ltd, 2021.

For re-use rights please refer to the publisher's terms and conditions.


© 2021 John Wiley & Sons Ltd. Facilities management (FM) of large public services is commonly outsourced to a specialist provider. Extensive data is collected on a wide range of operational tasks. Often, limited use is made of this data beyond operational considerations. Increasing availability of sophisticated data integration systems makes it possible to develop bespoke data science solutions to improve the efficiency, speed and accuracy of commonly encountered tasks. A Knowledge Transfer Partnership (a funding scheme of Innovate UK) was set-up between Newcastle University and a large FM provider. Within this project, data science has been effectively applied to improve service delivery in three different case studies: (1) designing routing algorithms for scheduling of staff allocation to jobs, (2) using natural language processing for automatically raising work orders from help desk emails, (3) development of algorithms to optimise the placement of charging points for the transition of fleets of commercial vehicles from diesel to electric powered. For each case study, we show how the data science work has contributed to improvement of FM by: (1) maximising the productivity of engineers, (2) reducing the time taken to process help desk emails, (3) creating a data-driven method to provide objective decision support for charger placement, respectively. The research in this paper is based on a contract with a local authority where the FM company provides planned and reactive maintenance for a range of assets in corporate buildings, hospitals and schools. In addition to describing the data science solutions, we will also discuss issues around knowledge transfer from data scientist to operational staff and how change management processes were employed in this project to embed the new working practices.

Publication metadata

Author(s): Walker D, Ruane M, Bacardit J, Coleman S

Publication type: Article

Publication status: Published

Journal: Quality and Reliability Engineering International

Year: 2021

Pages: Epub ahead of print

Online publication date: 04/10/2021

Acceptance date: 06/08/2021

Date deposited: 19/10/2021

ISSN (print): 0748-8017

ISSN (electronic): 1099-1638

Publisher: John Wiley and Sons Ltd


DOI: 10.1002/qre.2994


Altmetrics provided by Altmetric