Automatic classification of takeaway food outlet cuisine type using machine (deep) learning
View / Open Files
Publication Date
2021-12-15Journal Title
Machine Learning with Applications
ISSN
2666-8270
Publisher
Elsevier
Volume
6
Language
eng
Type
Article
This Version
VoR
Metadata
Show full item recordCitation
Bishop, T., von Hinke, S., Hollingsworth, B., Lake, A., Brown, H., & Burgoine, T. (2021). Automatic classification of takeaway food outlet cuisine type using machine (deep) learning. Machine Learning with Applications, 6 https://doi.org/10.1016/j.mlwa.2021.100106
Abstract
Background and purpose
Neighbourhood exposure to takeaway (‘fast’-) food outlets selling different cuisines may be differentially associated with diet, obesity and related disease, and contributing to population health inequalities. However research studies have not disaggregated takeaways by cuisine type. This is partly due to the substantial resource challenge of de novo manual classification of unclassified takeaway outlets at scale. We describe the development of a new model to automatically classify takeaway food outlets, by 10 major cuisine types, based on business name alone.
Material and methods
We used machine (deep) learning, and specifically a Long Short Term Memory variant of a Recurrent Neural Network, to develop a predictive model trained on labelled outlets (n=14,145), from an online takeaway food ordering platform. We validated the accuracy of predictions on unseen labelled outlets (n=4000) from the same source.
Results
Although accuracy of prediction varied by cuisine type, overall the model (or ‘classifier’) made a correct prediction approximately three out of four times. We demonstrated the potential of the classifier to public health researchers and for surveillance to support decision-making, through using it to characterise nearly 55,000 takeaway food outlets in England by cuisine type, for the first time.
Conclusions
Although imperfect, we successfully developed a model to classify takeaway food outlets, by 10 major cuisine types, from business name alone, using innovative data science methods. We have made the model available for use elsewhere by others, including in other contexts and to characterise other types of food outlets, and for further development.
Keywords
Classification, Data Science, Cuisine Type, Machine (Deep) Learning, Takeaway (‘Fast-’) Food Outlets, Universal Language Model Fine-tuning (Ulmfit)
Sponsorship
This study is funded by the National Institute of Health Research (NIHR) School of Public Health Research (Grant Reference Number PD-SPH-2015). The views expressed are those of the author(s) and not necessarily those of the NIHR or the Department of Health and Social Care. This work was also supported by the MRC Epidemiology Unit, University of Cambridge (Grant Reference Number MC/UU/00006/7). TBu is funded by the Centre for Diet and Activity Research (CEDAR), a UK Clinical Research Collaboration (UKCRC) Public Health Research Centre of Excellence. Funding from the British Heart Foundation, Cancer Research UK, Economic and Social Research Council, Medical Research Council, the National Institute of Health Research, and the Wellcome Trust (Grant Reference Number MR/K023187/1), under the auspices of the UK Clinical Research Collaboration, is gratefully acknowledged. These funders played no role in the study design; in the collection, analysis and interpretation of data; in the writing of the report; and in the decision to submit the article for publication.
Funder references
Medical Research Council (MR/K023187/1)
Department of Health (via National Institute for Health Research (NIHR)) (PD-SPH-2015-10029 BH154142)
MRC (MC_UU_00006/7)
Medical Research Council (MR/K02325X/1)
Identifiers
34977839, PMC8700226
External DOI: https://doi.org/10.1016/j.mlwa.2021.100106
This record's URL: https://www.repository.cam.ac.uk/handle/1810/333589
Statistics
Total file downloads (since January 2020). For more information on metrics see the
IRUS guide.