Abstract
Understanding and predicting consumer acceptance is critical to commercial success in the coffee industry. This study presents a robust data analysis framework to deconstruct consumer preference using a dataset where 118 consumers rated their liking of 27 black drip coffee samples, the adequacy of select attributes on just-about-right (JAR) scales, and the sensory profile of the coffees with a check-all-that-apply (CATA) task. We integrated four feature-ranking methods to identify key sensory drivers, which informed the development of predictive models to forecast consumer liking. A novel consumer segmentation technique was also introduced, applying k-Means clustering to consumers’ individual preference correlation vectors. JAR acidity, JAR flavor intensity, and CATA sweetness were found to be primary drivers of liking across the population (p-value < 1e-70). The resulting predictive models demonstrated strong performance even with a limited set of 3 sensory features. Consumers were clustered into two segments with contrasting preferences for 12 different sensory attributes. The proposed analytical pipeline provides a comprehensive approach to sensory and consumer data, enabling both the prediction of general consumer liking and the identification of distinct preference segments.
Similar content being viewed by others
Data availability
The dataset used in this study was sourced from and is available at: https://datadryad.org/dataset/doi:10.25338/B8993H.
Code availability
All code and instructions on how to reproduce the results can be found at https://github.com/mhgun/sensory_prediction.
References
“Coffee Year 2023/24,” International Coffee Organization, Sep. 2024. Accessed: Sep. 09, 2025. [Online]. Available: https://www.ico.org/documents/cy2024-25/annual-review-2023-2024-e.pdf.
Seninde, D. R. & Chambers, E. Coffee flavor: a review. Beverages 6, 44, https://doi.org/10.3390/beverages6030044 (2020).
Sunarharum, W. B., Williams, D. J. & Smyth, H. E. Complexity of coffee flavor: a compositional and sensory perspective. Food Res. Int. 62, 315–325, https://doi.org/10.1016/j.foodres.2014.02.030 (2014).
Geel, L., Kinnear, M. & de Kock, H. L. Relating consumer preferences to sensory attributes of instant coffee. Food Qual. Prefer. 16, 237–244, https://doi.org/10.1016/j.foodqual.2004.04.014 (2005).
Condelli, N. et al. Drivers of coffee liking: effect of physicochemical characteristics and aromatic profile on consumers’ acceptability of mono-origin and mono-variety coffees. J. Food Sci. 87, 4688–4702, https://doi.org/10.1111/1750-3841.16323 (2022).
Roman-Maldonado, Y., Gutiérrez-Salomón, A. L., Jaimez-Ordaz, J., García-Barrón, S. E. & Barajas-Ramírez, J. A. Drivers of liking to predict consumers’ acceptance of local coffee from indigenous Mexican regions. Eur. Food Res. Technol. 248, 467–475 (2022).
Spencer, M., Sage, E., Velez, M. & Guinard, J.-X. Using single free sorting and multivariate exploratory methods to design a new coffee taster’s flavor wheel. J. Food Sci. 81, S2997–S3005 (2016).
Cotter, A. R., Batali, M. E., Ristenpart, W. D. & Guinard, J.-X. Consumer preferences for black coffee are spread over a wide range of brew strengths and extraction yields. J. Food Sci. 86, 194–205 (2021).
J. Hoffmann, The world atlas of coffee. (Hachette, 2018).
Harwood, W. S., McLean, K. G., Ennis, J. M., Ennis, D. M. & Drake, M. Comparison of preference mapping with projective mapping for characterizing consumer perception of brewed black coffees. J. Sens. Stud. 35, e12563 (2020).
Lichters, M., Möslein, R., Sarstedt, M. & Scharf, A. Segmenting consumers based on sensory acceptance tests in sensory labs, immersive environments, and natural consumption settings. Food Qual. Prefer. 89, 104138 (2021).
Jaeger, S. R., Worch, T., Phelps, T., Jin, D. & Cardello, A. V. Preference segments among declared craft beer drinkers: perceptual, attitudinal and behavioral responses underlying craft-style vs. traditional-style flavor preferences. Food Qual. Prefer. 82, 103884 (2020).
van Kleef, E., van Trijp, H. C. M. & Luning, P. Internal versus external preference analysis: an exploratory study on end-user evaluation. Food Qual. Prefer. 17, 387–399 (2006).
Varela, P., Beltrán, J. & Fiszman, S. An alternative way to uncover drivers of coffee liking: Preference mapping based on consumers’ preference ranking and open comments. Food Qual. Prefer. 32, 152–159 (2014).
Bhumiratana, N., Wolf, M., Chambers IV, E. & Adhikari, K. Coffee drinking and emotions: are there key sensory drivers for emotions? Beverages 5, 27 (2019).
Guinard, J.-X. et al. A new coffee brewing control chart relating sensory properties and consumer liking to brew strength, extraction yield, and brew ratio. J. Food Sci. 88, 2168–2177 (2023).
Rothman, L. & Parker, M. J. Just-about-Right (JAR) Scales: Design, Usage, Benefits, and Risks. (ASTM International, 2009).
Lawless, H. T. & Heymann, H. Sensory Evaluation of Food: Principles and Practices. (Springer Science & Business Media, 2010).
Raschka, S. Model evaluation, model selection, and algorithm selection in machine learning. arXiv preprint arXiv:1811.12808 (2018).
Frost, S. C., Ristenpart, W. D. & Guinard, J.-X. Effects of brew strength, brew yield, and roast on the sensory quality of drip brewed coffee. J. Food Sci. 85, 2530–2543 (2020).
Batali, M. E., Ristenpart, W. D. & Guinard, J.-X. Brew temperature, at fixed brew strength and extraction, has little impact on the sensory profile of drip brew coffee. Sci. Rep. 10, 16450 (2020).
Batali, M. E., Frost, S. C., Lebrilla, C. B., Ristenpart, W. D. & Guinard, J.-X. Sensory and monosaccharide analysis of drip brew coffee fractions versus brewing time. J. Sci. Food Agric. 100, 2953–2962 (2020).
Oestreich, J. S. Chemistry of coffee. Reference Modul In Chemistry, Molecular Sciences Engineering 1–28 (2010).
Cordoba, N., Peterson, D. & Giuliano, P. “How Sweet Coffee Tastes! Towards an Understanding of Coffee Sweetness,” SCA News, vol. 25, no. 22, Oct. 2025, Accessed: Dec. 15, 2025. [Online]. Available: https://sca.coffee/sca-news/25/issue-22/understanding-coffee-sweetness.
Ristenpart, W. D., Cotter, A. R. & Guinard, J.-X. Impact of beverage temperature on consumer preferences for black coffee. Sci. Rep. 12, 20621 (2022).
Batali, M. E., Cotter, A. R., Frost, S. C., Ristenpart, W. D. & Guinard, J.-X. Titratable acidity, perceived sourness, and liking of acidity in drip brewed coffee. ACS Food Sci. Technol. 1, 559–569 (2021).
Barahona, I., Sanmiguel Jaimes, E. M. & Yang, J. Sensory attributes of coffee beverages and their relation to price and package information: a case study of Colombian customers’ preferences. Food Sci. Nutr. 8, 1173–1186 (2020).
Bichlmaier, C. et al. Contribution of mozambioside roasting products to coffee’s bitter taste. Food Chem. 469, 142547 (2025).
Liang, J., Batali, M. E., Routt, C., Ristenpart, W. D. & Guinard, J.-X. Sensory analysis of the flavor profile of full immersion hot, room temperature, and cold brewed coffee over time. Sci. Rep. 14, 19298 (2024).
Peryam, D. R. & Girardot, N. F. Advanced taste-test method. Food Eng. 7, 58–61 (1952).
Peryam, D. R. & Pilgrim, F. J. Hedonic scale method of measuring food preferences. Food Technol. 11, 9–14 (1957).
Guyon, I., Weston, J., Barnhill, S. & Vapnik, V. Gene selection for cancer classification using support vector machines. Mach. Learn. 46, 389–422 (2002).
Platt, J. et al. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classif. 10, 61–74 (1999).
Zhang, H. The optimality of naive Bayes. Aa 1, 3 (2004).
Freund, Y., Schapire, R. & Abe, N. A short introduction to boosting. J. -Jpn. Soc. Artif. Intell. 14, 1612 (1999).
G. E. Hinton, “Connectionist learning procedures,” in Machine Learning (pp. 555–610) (Elsevier, 1990).
Breiman, L. Random forests. Mach. Learn. 45, 5–32 (2001).
Liu, F. T., Ting, K. M. & Zhou, Z.-H. “Isolation Forest,” in 2008 Eighth IEEE International Conference on Data Mining, (pp. 413–422) (IEEE, 2008).
Breunig, M. M., Kriegel, H.-P., Ng, R. T. & Sander, J. “LOF: identifying density-based local outliers,” in Proc. 2000 ACM SIGMOD International Conference on Management of Data, in SIGMOD ’00. (pp. 93–104) (Association for Computing Machinery, 2000).
Satopaa, V., Albrecht, J., Irwin, D. & Raghavan, B. “Finding a” kneedle” in a haystack: Detecting knee points in system behavior,” in 2011 31st International Conference On Distributed Computing Systems Workshops, (pp. 166–171) (IEEE, 2011).
Lloyd, S. Least squares quantization in PCM. IEEE Trans. Inf. Theory 28, 129–137 (1982).
Rousseeuw, P. J. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53–65 (1987).
Caliński, T. & Harabasz, J. A dendrite method for cluster analysis. Commun. Stat. 3, 1–27 (1974).
Schwarz, G. “Estimating the dimension of a model,” Ann. Stat. 6, 461–464 (1978).
Acknowledgements
The authors declare that financial support was received for the research, authorship, and/or publication of this article. This work was supported by the United States Department of Agriculture-National Institute of Food and Agriculture AI Institute for Next Generation Food Systems (AIFS), USDA-NIFA award number 2020–67021-32855 to I.T. We would like to thank the members of the Tagkopoulos lab for helpful discussions and comments, as well as Fangzhou Li for his work in developing the Model Selection and Analysis pipeline.
Author information
Authors and Affiliations
Contributions
M.G. designed and performed preliminary analysis, performed all computational analysis, and created figures. M.S. and J.X.G. framed the sensory and consumer data for subsequent analyses. J.X.G. and I.T. conceived and supervised all aspects of the project. M.G. wrote the initial manuscript, and M.S., J.X.G., and I.T. edited it.
Corresponding authors
Ethics declarations
Competing interests
Author Guinard was the senior author of the Cotter et al. publication from which the publicly available data for this study were sourced. The other authors do not have a competing interest.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Gunning, M., Laforgue, M.P.S., Guinard, JX. et al. AI-driven prediction of consumer liking of coffee from sensory data. npj Sci Food (2026). https://doi.org/10.1038/s41538-026-00779-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41538-026-00779-7
