IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v18y2025i12p3054-d1675189.html
   My bibliography  Save this article

Machine Learning with Administrative Data for Energy Poverty Identification in the UK

Author

Listed:
  • Lin Zheng

    (UCL Energy Institute, University College London, 14 Upper Woburn Place, London WC1H 0NN, UK)

  • Eoghan McKenna

    (UCL Energy Institute, University College London, 14 Upper Woburn Place, London WC1H 0NN, UK)

Abstract

Energy poverty continues to be a critical challenge, and this requires efficient and scalable identification methods to support targeted interventions. The Low Income Low Energy Efficiency (LILEE) indicator and previously the Low Income High Costs (LIHC) indicator have been used by the UK government to monitor national energy poverty levels. Yet due to their reliance on complex, time-intensive data collection processes and estimations, these indicators are not suitable for identifying energy poverty in specific households. This study investigates an alternative approach to energy poverty identification: using machine learning models trained on administrative data, data that could reasonably be available to governments for all or most households. We develop machine learning models using data from the English Housing Survey that serves as a proxy for administrative data. This data is selected to closely resemble what might be available in national administrative databases, incorporating variables such as household socio-demographics and building physical characteristics. We evaluate multiple classification algorithms, including Random Forest and XGBoosting, applying resampling and class weighting techniques to address the inherent class imbalance in energy poverty classification. We compare model performance with a ‘benchmark’ model developed by the UK government for the same goal. Model performance is assessed using the metrics of accuracy, balanced accuracy, precision, recall, and F1-score, with SHapley Additive exPlanations (SHAP) values providing the interpretability of the predictions. The best-performing model (XGBoosting with class weighting) achieves higher balanced accuracy (0.88), and precision (0.51) compared to the benchmark model (balanced accuracy: 0.77, precision: 0.24), demonstrating an improved ability to classify energy-poor households with fewer data constraints. SHAP analysis reveals household income and dwelling characteristics are key determinants of energy poverty. This research demonstrates that machine learning, trained on existing administrative datasets, offers a feasible, scalable, and interpretable alternative for energy poverty identification, enabling new opportunities for efficient targeted policy interventions. This study also aligns with recent UK government discussions on the potential for integrating administrative data sources to enhance policy implementation. Future research could explore the integration of real-time smart meter data to refine energy poverty assessments further.

Suggested Citation

  • Lin Zheng & Eoghan McKenna, 2025. "Machine Learning with Administrative Data for Energy Poverty Identification in the UK," Energies, MDPI, vol. 18(12), pages 1-26, June.
  • Handle: RePEc:gam:jeners:v:18:y:2025:i:12:p:3054-:d:1675189
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/18/12/3054/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/18/12/3054/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Camboni, Riccardo & Corsini, Alberto & Miniaci, Raffaele & Valbonesi, Paola, 2021. "Mapping fuel poverty risk at the municipal level. A small-scale analysis of Italian Energy Performance Certificate, census and survey data," Energy Policy, Elsevier, vol. 155(C).
    2. Wang, Hanjie & Maruejols, Lucie & Yu, Xiaohua, 2021. "Predicting energy poverty with combinations of remote-sensing and socioeconomic survey data in India: Evidence from machine learning," Energy Economics, Elsevier, vol. 102(C).
    3. Abbas, Khizar & Butt, Khalid Manzoor & Xu, Deyi & Ali, Muhammad & Baz, Khan & Kharl, Sanwal Hussain & Ahmed, Mansoor, 2022. "Measurements and determinants of extreme multidimensional energy poverty using machine learning," Energy, Elsevier, vol. 251(C).
    4. Moore, Richard, 2012. "Definitions of fuel poverty: Implications for policy," Energy Policy, Elsevier, vol. 49(C), pages 19-26.
    5. Ge, Jianping & Lei, Yalin, 2013. "Mining development, income growth and poverty alleviation: A multiplier decomposition technique applied to China," Resources Policy, Elsevier, vol. 38(3), pages 278-287.
    6. Spandagos, Constantine & Tovar Reaños, Miguel & Lynch, Muireann Á, 2023. "Energy poverty prediction and effective targeting for just transitions with machine learning," Papers WP762, Economic and Social Research Institute (ESRI).
    7. Spandagos, Constantine & Tovar Reaños, Miguel Angel & Lynch, Muireann Á., 2023. "Energy poverty prediction and effective targeting for just transitions with machine learning," Energy Economics, Elsevier, vol. 128(C).
    8. Waddams Price, Catherine & Brazier, Karl & Wang, Wenjia, 2012. "Objective and subjective measures of fuel poverty," Energy Policy, Elsevier, vol. 49(C), pages 33-39.
    9. Dalla Longa, Francesco & Sweerts, Bart & van der Zwaan, Bob, 2021. "Exploring the complex origins of energy poverty in The Netherlands with machine learning," Energy Policy, Elsevier, vol. 156(C).
    10. Kelly, Scott & Crawford-Brown, Doug & Pollitt, Michael G., 2012. "Building performance evaluation and certification in the UK: Is SAP fit for purpose?," Renewable and Sustainable Energy Reviews, Elsevier, vol. 16(9), pages 6861-6878.
    11. Sovacool, Benjamin K., 2015. "Fuel poverty, affordability, and energy justice in England: Policy insights from the Warm Front Program," Energy, Elsevier, vol. 93(P1), pages 361-371.
    12. Hajkowicz, Stefan A. & Heyenga, Sonja & Moffat, Kieren, 2011. "The relationship between mining and socio-economic well being in Australia's regions," Resources Policy, Elsevier, vol. 36(1), pages 30-38, March.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Budría, Santiago & Bravo Chew, Leslie, 2025. "Enduring Inequalities: Analyzing Energy Poverty Inertia Across K-Means Clusters," IZA Discussion Papers 17809, Institute of Labor Economics (IZA).
    2. Li, Jiajia & Yang, Shiyu & Li, Jun & Li, Houjian, 2024. "Targeting SDG7: Identifying heterogeneous energy dilemmas for socially disadvantaged groups in India using machine learning," Energy Economics, Elsevier, vol. 138(C).
    3. Balkissoon, Sarah & Fox, Neil & Lupo, Anthony & Haupt, Sue Ellen & Penny, Stephen G. & Miller, Steve J. & Beetstra, Margaret & Sykuta, Michael & Ohler, Adrienne, 2024. "Forecasting energy poverty using different machine learning techniques for Missouri," Energy, Elsevier, vol. 313(C).
    4. Takako Mochida & Andrew Chapman & Benjamin Craig McLellan, 2025. "Exploring Energy Poverty: Toward a Comprehensive Predictive Framework," Energies, MDPI, vol. 18(10), pages 1-23, May.
    5. Recep Ulucak & Ramazan Sari & Seyfettin Erdogan & Rui Alexandre Castanho, 2021. "Bibliometric Literature Analysis of a Multi-Dimensional Sustainable Development Issue: Energy Poverty," Sustainability, MDPI, vol. 13(17), pages 1-21, August.
    6. Karásek, Jiří & Pojar, Jan, 2018. "Programme to reduce energy poverty in the Czech Republic," Energy Policy, Elsevier, vol. 115(C), pages 131-137.
    7. Deller, David & Turner, Glen & Waddams Price, Catherine, 2021. "Energy poverty indicators: Inconsistencies, implications and where next?," Energy Economics, Elsevier, vol. 103(C).
    8. Urszula Grzybowska & Agnieszka Wojewódzka-Wiewiórska & Gintarė Vaznonienė & Hanna Dudek, 2024. "Households Vulnerable to Energy Poverty in the Visegrad Group Countries: An Analysis of Socio-Economic Factors Using a Machine Learning Approach," Energies, MDPI, vol. 17(24), pages 1-23, December.
    9. Okushima, Shinichiro, 2017. "Gauging energy poverty: A multidimensional approach," Energy, Elsevier, vol. 137(C), pages 1159-1166.
    10. Spandagos, Constantine & Tovar Reaños, Miguel Angel & Lynch, Muireann Á., 2023. "Energy poverty prediction and effective targeting for just transitions with machine learning," Energy Economics, Elsevier, vol. 128(C).
    11. Camboni, Riccardo & Corsini, Alberto & Miniaci, Raffaele & Valbonesi, Paola, 2021. "Mapping fuel poverty risk at the municipal level. A small-scale analysis of Italian Energy Performance Certificate, census and survey data," Energy Policy, Elsevier, vol. 155(C).
    12. Burlinson, Andrew & Giulietti, Monica & Law, Cherry & Liu, Hui-Hsuan, 2021. "Fuel poverty and financial distress," Energy Economics, Elsevier, vol. 102(C).
    13. Best, Rohan & Sinha, Kompal, 2021. "Fuel poverty policy: Go big or go home insulation," Energy Economics, Elsevier, vol. 97(C).
    14. Okushima, Shinichiro, 2016. "Measuring energy poverty in Japan, 2004–2013," Energy Policy, Elsevier, vol. 98(C), pages 557-564.
    15. Fu Wang & Hong Geng & Donglan Zha & Chaoqun Zhang, 2023. "Multidimensional Energy Poverty in China: Measurement and Spatio-Temporal Disparities Characteristics," Social Indicators Research: An International and Interdisciplinary Journal for Quality-of-Life Measurement, Springer, vol. 168(1), pages 45-78, August.
    16. Elpida Kalfountzou & Lefkothea Papada & Christos Tourkolias & Sevastianos Mirasgedis & Dimitris Kaliampakos & Dimitris Damigos, 2025. "A Comparative Analysis of Machine Learning Algorithms in Energy Poverty Prediction," Energies, MDPI, vol. 18(5), pages 1-20, February.
    17. Du, Juntao & Song, Malin & Xie, Bing, 2022. "Eliminating energy poverty in Chinese households: A cognitive capability framework," Renewable Energy, Elsevier, vol. 192(C), pages 373-384.
    18. Yiming Xiao & Han Wu & Guohua Wang & Hong Mei, 2021. "Mapping the Worldwide Trends on Energy Poverty Research: A Bibliometric Analysis (1999–2019)," IJERPH, MDPI, vol. 18(4), pages 1-22, February.
    19. Paudel, Jayash, 2021. "Why Are People Energy Poor? Evidence From Ethnic Fractionalization," Energy Economics, Elsevier, vol. 102(C).
    20. Paul Simshauser, 2022. "The 2022 energy crisis: horizontal and vertical impacts of policy interventions in Australia's national electricity market," Working Papers EPRG2216, Energy Policy Research Group, Cambridge Judge Business School, University of Cambridge.

    More about this item

    Keywords

    ;
    ;
    ;
    ;
    ;

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:18:y:2025:i:12:p:3054-:d:1675189. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.