UDC 004.8
UDC 658.8
The article explores modern machine learning methods used for modeling consumer choice, including artificial neural networks and approaches to synthesizing expert judgments. Particular attention is paid to the combination of neural models with classical decision analysis approaches to improve prediction accuracy. The paper provides an overview of neural network architectures applied to consumer preference modeling and discusses hybrid method cases in e-commerce. The effectiveness of integrating expert knowledge into machine learning structures is substantiated.
machine learning, consumer choice, expert judgments, neural networks, data mining
1. McFadden D. Conditional logit analysis of qualitative choice behavior // V kn.: Zarembka P. (red.) Frontiers in Econometrics. New York: Academic Press, 1974. S. 105–142.
2. Gan C., Limsombunchai V., Clemes M., Weng A. Consumer Choice Prediction: Artificial Neural Networks versus Logistic Models // Journal of Social Sciences. 2005. T. 1, № 4. S. 211–219.
3. Kolmakov I.B., Domozhakov M.V. Sintez ekonometricheskih i neyrosetevyh modeley prognoza pokazateley sfery issledovaniy i innovaciy v Rossiyskoy Federacii // Upravlencheskie nauki. 2016. № 2(19). S. 27–37.
4. Han Y., Pereira F.C., Ben-Akiva M., Zegras C. A neural-embedded discrete choice model: Learning taste representation with strengthened interpretability // Transportation Research Part B: Methodological. 2022. T. 163. S. 166–186.
5. Hairova S.M., Hairov B.G., Shimohin A.V. Metodika raboty s postavschikami na osnove modelirovaniya raboty neyronnoy seti pri reshenii voprosov vybora postavschikov uslug // Fundamental'nye issledovaniya. 2020. № 7. S. 129–137.
6. LeCun Y., Bengio Y., Hinton G. Deep learning // Nature. 2015. T. 521, № 7553. S. 436–444.
7. Greene M.N., Morgan P.H., Foxall G.R. Neural Networks and Consumer Behavior: Neural Models, Logistic Regression, and the Behavioral Perspective Model // The Behavior Analyst. 2017. T. 40, № 2. S. 393–418.
8. Hu M.Y., Tsoukalas C. Explaining consumer choice through neural networks: The stacked generalization approach // European Journal of Operational Research. 2003. T. 146, № 3. S. 650–660.
9. Hruschka H. Using a heterogeneous multinomial probit model with a neural net extension to model brand choice // Journal of Forecasting. 2007. T. 26, № 2. S. 113–127.
10. Qian F., Xu L. Improving customer satisfaction by the expert system using artificial neural networks // WSEAS Transactions on Business and Economics. 2007. T. 4, № 10. S. 147–151.
