Wine recommendation algorithm based on partitioning and stacking integration strategy for Chinese wine consumers

Main Article Content

Weisong Mu
Yumeng Feng
Haojie Shu
Bo Wang
Dong Tian

Keywords

Chinese consumers, machine learning, preference for wine attributes, Recommendation algorithm, Stacking integration

Abstract

This study tries to propose a wine recommendation algorithm based on partitioning and Stacking Integration Strategy for Chinese wine consumers. The approaches follow the idea of partitioning, decomposing traditional recommendation task into several subtasks according to wine attributes, using neural network, support vector machine (SVM), decision tree, random forest, optimized random forest, Adaboost and XGBoost as recommendation models. Then, based on Stacking integration method, five models are screened out for each recommendation index as the base classifier, and the decision tree or logistic regression model is selected as the meta-learner to construct a two-layer Stacking integration framework. Finally, the optimal recommendation algorithm be built for recommendation subtasks according to the prediction accuracy. The result showed that the Stacking integrated recommendation model was suitable for the recommendation of eight attributes including colour, sweetness, foamability, mouthfeel, aroma type, year, packaging and brand, while SVM model was suitable to recommend aroma concentration and price, and the XGboost model was most appropriate for origin. This study would subserve consumers to choose the wine more easily and conveniently and provide support for wine companies to improve customer satisfaction with consumer services. The study expands the approach of concerning research and proposes a specific multi-model recommendation strategy based on artificial intelligence models to recommend multiattribute commodities.

Abstract 259 | PDF Downloads 201 HTML Downloads 117 XML Downloads 8

References

Ahmadi, E., Garcia-Arce, A., Masel, D.T., Reich, E., Puckey, J. and Maff, R. 2019. A metaheuristic-based stacking model for predicting the risk of patient no-show and late cancellation for neurology appointments. IISE Transactions on Healthcare Systems Engineering. 9(3): 272–291. 10.1080/24725579.2019.1649764

Areta, A., Bardaji, I. and Iraizoz, B. 2017. Spanish wines in the US market: what attributes do US consumers look for in Spanish wines? Spanish Journal of Agricultural Research. 15(4): e0120. 10.5424/sjar/2017154-10006

Cai, J., Pang, J., Hu, K. and Tao, Y. 2015. Chinese familiarity with wine aromas characteristics. Journal of Food Science and Technology. 33(04):47–51.

Capitello, R., Bazzani, C. and Begalli, D. 2019. Consumer personality, attitudes and preferences in out-of-home contexts. International Journal of Wine Business Research. 31(1): 48–67. 10.1108/IJWBR-06-2018-0022

Chu, X., Li, Y., Xie, Y., Tian, D. and Mu, W. 2020. Regional difference analyzing and prediction model building for Chinese wine consumers’ sensory preference. British Food Journal. 122(8): 2587–2602. 10.1108/BFJ-06-2019-0465

Diez, F.J., Navas-Gracia, L.M., Martinez-Rodriguez, A., Correa-Guimaraes, A. and Chico-Santamarta, L. 2019. Modelling of a flat-plate solar collector using artificial neural networks for different working fluid (water) flow rates. Solar Energy. 188: 1320–1331. 10.1016/j.solener.2019.07.022

Gustafson, C.R., Lybbert, T.J. and Sumner, D.A. 2016. Consumer sorting and hedonic valuation of wine attributes: exploiting data from a field experiment. Agricultural Economics. 47(1): 91–103. 10.1111/agec.12212

Hao, L., Fang, Y. and Zhang, Q. 2021. Rediscussion on statistical measure on Gini coefficient. Statistics & Decision. 37(7): 27–32.

He, Y., Zou, H. and Yu, H. 2019. Recommender system model based on dynamic-weighted bagging matrix factorization. Journal of Nanjing University (Natural Science). 55(04): 644–650.

Hu, Y., Qu, B., Liang, J., Wang, J. and Wang, Y. 2021. A survey on evolutionary ensemble learning algorithm. Chinese Journal of Intelligent Science and Technology. 3(1):18–33.

Janitza, S., Tutz, G. and Boulesteix, A. 2016. Random forest for ordinal responses: prediction and variable selection. Computational Statistics and Data Analysis. 96(C): 57–73.

Lee, S.J. and Lee, K.G. 2008. Understanding consumer preferences for rice wines using sensory data. Journal of the Science of Food and Agriculture. 88(4): 690–698. 10.1002/jsfa.3137

Li, Q. and Zhai, L. 2019. Analysis and research on employee turnover prediction based on stacking algorithm. Journal of Chongqing Technology and Business University (Natural Science Edition). 36(01): 117–123.

Li, Y., Jia, X., Wang, R., Qi, J., Jin, H., Chu, X. and Mu, W. 2022. A new oversampling method and improved radial basis function classifier for customer consumption behavior prediction. Expert Systems with Applications. 199: 116982. 10.1016/j.eswa.2022.116982

Liao, H. and Zhou, D. 2012. Review of AdaBoost and its improvement. Computer Systems & Applications. 21: 240–244.

Liu, H., Guo, M. and Pan, W. 2017. Overview of personalized recommendation systems. Journal of Changzhou University (Natural Science Edition). 29: 51–59.

Mehta, R. and Bhanja, N. 2018. Consumer preferences for wine attributes in an emerging market. International Journal of Retail & Distribution Management. 46(1): 34–48. 10.1108/IJRDM-04-2017-0073

Meng, Q. and Xiong, H. 2021. Doctor recommendation based on online consultation text information. Information Science. 39(06): 152–160.

Montesinos-López, O.A., Montesinos-López, A., Crossa, J., Cuevas J., Montesinos-López, J.C., Gutiérrez, Z.S., Lillemo, M., Philomin, J. and Singh, R. 2019. A Bayesian genomic multi-output regressor stacking model for predicting multi-trait multi-environment plant breeding data. G3 (Bethesda). 9(10): 3381–3393. 10.1534/g3.119.400336

Pagan, K.M., Giraldi, J.D.M.E., Maheshwari, V., de Paula, A.L.D. and de Oliveira, J.H.C. 2021. Evaluating cognitive processing and preferences through brain responses towards country of origin for wines: the role of gender and involvement. International Journal of Wine Business Research. 33(4): 481–501. 10.1108/IJWBR-08-2020-0043

Pascoal, C., Oliveira, M.R., Pacheco, A. and Valadas, R. 2017. Theoretical evaluation of feature selection methods based on mutual information. Neurocomputing. 226: 168–181.

Portugal, I., Alencar, P. and Cowan, D. 2018. The use of machine learning algorithms in recommender systems: A systematic review. Expert Systems with Application. 97: 205–227. 10.1016/j.eswa.2017.12.020

Rodríguez-Donate, M.C., Romero-Rodríguez, M.E. and Cano-Fernández, V.J. 2021. Wine consumption preferences among generations X and Y: an analysis of variability. British Food Journal. 123(11): 3557–3575. 10.1108/BFJ-12-2020-1156

Roy, M. and Larocque, D. 2012. Robustness of random forests for regression. Journal of Nonparametric Statistics. 24(4): 93–1006. 10.1080/10485252.2012.715161

Stanco, M., Lerro, M. and Marotta, G. 2020. Consumers’ preferences for wine attributes: a best–worst scaling analysis. Sustain-ability. 12(7): 2819. 10.3390/su12072819

Szolnoki, G. and Hauck, K. 2020. Analysis of German wine consumers’ preferences for organic and non-organic wines. British Food Journal. 122(7): 2077–2087. 10.1108/BFJ-10-2019-0752

Tao, Y., Peng, Y., Jiang, Q., Li, Y., Fang, S. and Gong, Y. 2019. Remote detection of critical growth stages in rapeseed using vegetation spectral and stacking combination method. Journal of Geomatics. 44(5): 20–23.

Wang, Y., Liao, X. and Li, S. B. 2019. Resealed boosting in classification. IEEE Transactions on Neural Networks and Learning Systems. 30(9): 2598–2610.

Xie, W., Chai, Q., Gan, Y., Chen, S., Zhang, X. and Wang, W. 2020. Strains classification of Anoectochilus roxburghii using multi-feature extraction and Stacking ensemble learning. Transactions of the Chinese Society of Agricultural Engineering. 36: 203–210.

Yang, F.J. & IEEE. 2019. An extended idea about decision trees. 2019 6TH INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE (CSCI 2019). 6th Annual Conference on Computational Science and Computational Intelligence (CSCI 2019). 349–354.

Yin, C., Guo, Y., Yang, J. and Ren, X. 2018. A new recommendation system on the basis of consumer initiative decision based on an associative classification approach. Industrial Management & Data Systems. 118(1): 188–203. 10.1108/IMDS-02-2017-0057

Zhang, J. and Lei, J. 2021. Stacking Fusion Model for customer purchase behavior prediction. Shanghai Management Science. 43: 12–19.