Using Machine Learning to Model the Acceptance of Domestic Low-Carbon Technologies - Article

Aug 3, 2026

Upload by Quinn

This research addresses two knowledge gaps in domestic low-carbon technology (LCT) adoption: how installation approaches and occupier status shape user acceptance, and how machine-learning methods can strengthen model-based understanding. Using an online quasi-experiment with 3813 English residents, the study builds and evaluates models of adoption intention, willingness to accept, willingness to pay, attitude, subjective norm, and perceived behavioural control. Two virtual reality technology implementations (new-build vs retrofit) capture differing installation approaches. Machine learning performance is compared across nine validation and predictor-selection techniques; LASSO yields near-optimal fit. Attitude, subjective norm, and perceived behavioural control significantly predict adoption intention, while installation approach affects acceptance intent and homeownership and age influence key outcomes, informing policy and future research.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages34

Reading Time1 h 26 min

AccessFree to download

Introduction

Abstract

Keywords

Methodology and Data

Machine learning techniques and validation

Virtual reality technology implementation

Findings and Interpretation

Predictors of adoption intention and acceptance

Effects of installation approach and occupier status

Implications for Policy and Future Research

Article Using Machine Learning to Model the Acceptance of Domestic Low-Carbon Technologies Paul van Schaik 1, *, Heather Clements 1, Yordanka Karayaneva 2, Elena Imani 3, Michael Knowles 4, Natasha Vall 5 and Matthew Cotton 6 Academic Editors: Augusto Montisciand Changning Wu Received: 5 May 2025 Revised: 11 July 2025 Accepted: 16 July 2025 Published: 22 July 2025 Citation: Schaik, P.v.; Clements, H.; Karayaneva, Y.; Imani, E.; Knowles, M.; Vall, N.; Cotton, M. Using Machine Learning to Model the Acceptance of Domestic Low-Carbon Technologies. Sustainability 2025, 17, 6668. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)su17156668 Copyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) . 1 Department of Psychology, Teesside University, Middlesbrough TS1 3BX, UK; [h.clements@tees.ac.uk](h.clements@tees.ac.uk) 2 Department of Computing and Games, Teesside University, Middlesbrough TS1 3BX, UK; [y.karayaneva@tees.ac.uk](y.karayaneva@tees.ac.uk) 3 Engineering Department, Teesside University, Middlesbrough TS1 3BX, UK; [e.imani@tees.ac.uk](e.imani@tees.ac.uk) 4 School of Computing and Engineering, Teesside University, Middlesbrough TS1 3BX, UK; [m.knowles@tees.ac.uk](m.knowles@tees.ac.uk) 5 Faculty of Liberal Arts and Sciences, University of Greenwich, London SE10 9LS, UK; [n.t.vall@gre.ac.uk](n.t.vall@gre.ac.uk) 6 Department of Humanities and Social Sciences, Teesside University, Middlesbrough TS1 3BX, UK; [m.cotton@tees.ac.uk](m.cotton@tees.ac.uk) * [Correspondence: p.van-schaik@tees.ac.uk](Correspondence: p.van-schaik@tees.ac.uk); Tel.: +44-1642-342320 Abstract This research addresses two specific knowledge gaps. The first regards the influence of domestic low-carbon technology (LCT) installation approaches and occupier status on user acceptance. The second is to demonstrate the role of machine learning techniques in producing an enhanced model-based understanding of domestic LCT acceptance. Together, these two approaches provide new insights into LCT acceptance through the theory of planned behaviour and demonstrate the value of machine learning for modelling such acceptance. Our aim is therefore to contribute to model-based knowledge about the acceptance of domestic LCTs. Specifically, we contribute new knowledge of the acceptance of LCTs according to the theory of planned behaviour and of the value of machine-learning techniques for modelling this acceptance. Through empirical research using an online quasi-experiment with 3813 English residents, we developed a model of low-carbon technology adoption and evaluated machine learning for model analysis. The design factors were the installation approach and occupier status, with main outcomes including adoption intention, willingness to accept, willingness to pay, attitude, subjective norm, and perceived behavioural control. To examine residents’ technology acceptance, we created two virtual reality models of technology implementation, differing in installation approach. For machine learning analysis, we employed nine techniques for model validation and predictor selection: linear regression, LASSO regression, ridge regression, support vector regression, regression tree (decision tree regression), random forest, XGBoost, k-NN, and neural network. LASSO regression emerged as the best technique in terms of predictor selection, with (near-)optimal model fit (R2 and MSE) . We found that attitude, subjective norm, and perceived behavioural control significantly predicted the intention to adopt low-carbon technologies. The installation approach influenced willingness to accept, with higher intention for new-build installations than retrofits.

FAQs

What gaps does the study aim to address about domestic low-carbon technologies?

It targets how installation approaches and occupier status influence user acceptance, and how machine-learning techniques can improve model-based understanding of LCT acceptance.

How was user acceptance measured in the research?

The study used an online quasi-experiment with 3813 English residents and created two virtual reality models of technology implementation that differed by installation approach.

Which machine-learning technique performed best for predictor selection and model fit?

LASSO regression emerged as the best technique, providing (near-)optimal model fit using validation and predictor selection results.

Aug 3, 2026

Upload by Quinn