Construction of a Dynamic Hybrid Model for Analyzing the Demand of Chinese NEV Consumers: Based on DS-Kano and C2SLM-Kano

Jin Liu; Xinyu Zhang; Xu Zhao; Zhiguo Liu; Xiaoyun Jiang; Jin Liu; Xinyu Zhang; Xu Zhao; Zhiguo Liu; Xiaoyun Jiang

doi:10.3934/jimo.2026047

Journal of Industrial and Management Optimization

2026, Volume 22, Issue 3: 1284-1301. doi: 10.3934/jimo.2026047

Previous Article Next Article

Research article Special Issues

Construction of a Dynamic Hybrid Model for Analyzing the Demand of Chinese NEV Consumers: Based on DS-Kano and C2SLM-Kano

1.
School of Economics and Management, Changchun Finance College, Jilin Province, Changchun City, Wukaihe Street No.1666, China
2.
Project Management Department, FAW-Volkswagen, Jilin Province, Changchun City, Anqing Street No.5, China

Received: 25 September 2025 Revised: 10 January 2026 Accepted: 27 January 2026 Published: 10 February 2026
62H30, 68T10, 62M10, 91B82, 90B20

Against the backdrop of the rapidly expanding global new energy vehicle (NEV) market in 2024–2025, consumer demand behavior exhibits dynamic regional variability, challenging traditionally static and homogeneous analytical approaches. This research introduces a dynamic hybrid model that combines dynamic-scenario Kano (DS-Kano) and correlation clustering sparse learning Kano (C2SLM-Kano) to tackle this issue. DS-Kano combines long short-term memory (LSTM) and deep reinforcement learning (DRL) for minute-level responsiveness to demand shifts. C2SLM-Kano uses graph convolutional network (GCN) clustering to quantify regional and cultural differences. Empirical validation showed that DS-Kano achieves 7.3 min latency (vs. 45 min for BERT-TCBAD-Kano and 360 min for traditional Kano), C2SLM-Kano reaches 89.2% cross-regional prediction accuracy, and the hybrid model improves demand identification F1-score by 30%, shortening product iteration time by 67% as shown by simulation-based evidence. Robustness checks confirm stability under data perturbations, algorithm swapping, and cross-regional validation. Practical implications should be considered by manufacturers to guide adaptive R&D and by policymakers to design targeted subsidies with case-informed estimates of policy effectiveness.
- new energy vehicles,
- dynamic Kano model,
- consumer demand analysis,
- scenario adaptation,
- regional cultural differences,
- LSTM-DRL,
- GCN clustering
Citation: Jin Liu, Xinyu Zhang, Xu Zhao, Zhiguo Liu, Xiaoyun Jiang. Construction of a Dynamic Hybrid Model for Analyzing the Demand of Chinese NEV Consumers: Based on DS-Kano and C2SLM-Kano[J]. Journal of Industrial and Management Optimization, 2026, 22(3): 1284-1301. doi: 10.3934/jimo.2026047

Related Papers:

Abstract

Against the backdrop of the rapidly expanding global new energy vehicle (NEV) market in 2024–2025, consumer demand behavior exhibits dynamic regional variability, challenging traditionally static and homogeneous analytical approaches. This research introduces a dynamic hybrid model that combines dynamic-scenario Kano (DS-Kano) and correlation clustering sparse learning Kano (C2SLM-Kano) to tackle this issue. DS-Kano combines long short-term memory (LSTM) and deep reinforcement learning (DRL) for minute-level responsiveness to demand shifts. C2SLM-Kano uses graph convolutional network (GCN) clustering to quantify regional and cultural differences. Empirical validation showed that DS-Kano achieves 7.3 min latency (vs. 45 min for BERT-TCBAD-Kano and 360 min for traditional Kano), C2SLM-Kano reaches 89.2% cross-regional prediction accuracy, and the hybrid model improves demand identification F1-score by 30%, shortening product iteration time by 67% as shown by simulation-based evidence. Robustness checks confirm stability under data perturbations, algorithm swapping, and cross-regional validation. Practical implications should be considered by manufacturers to guide adaptive R&D and by policymakers to design targeted subsidies with case-informed estimates of policy effectiveness.

References

[1]	International Energy Agency. Global Electric Vehicle Outlook 2025, 2025. Available from: https://www.iea.org/reports/global-ev-outlook-2025.
[2]	China Passenger Car Association. China New Energy Passenger Vehicle Market Report 2024, 2024. Available from: https://www.marklines.com/en/report/cpca062_202412.
[3]	China Association of Automobile Manufacturers (CAAM). Annual Report on China's New Energy Vehicle Market. Beijing. CAAM Press, 2024. Available from: https://link.springer.com/book/9789819682324.
[4]	National Development and Reform Commission of China. Policy Support for New Energy Vehicles in China 2024, 2024. Available from: https://climatecooperation.cn/climate/new-policy-supports-the-integration-of-new-energy-vehicles-into-the-power-grid/.
[5]	State Council of China. New Energy Vehicle Industry Development Plan 2021–2035, 2021. Available from: https://www.chinajusticeobserver.com/law/x/new-energy-vehicle-industry-development-plan-20201009/chn.
[6]	Y. Lou, W. Wang, X. Yang. Customers' attitude on new energy vehicles' policies and policy impact on customers' purchase intention, Energy Procedia, 105 (2017), 2187–2193. https://doi.org/10.1016/j.egypro.2017.03.617 doi: 10.1016/j.egypro.2017.03.617
[7]	The State Council of PRC, China sees 47.6-pct rise in NEV charging infrastructure facilities, 2025. Available from: https://english.www.gov.cn/archive/statistics/202505/03/content_WS6815b388c6d0868f4e8f2449.html.
[8]	S. Li, Transportation justice for sustainable cities: An equity review of EV charging infrastructure in China, Sustainable Cities Soc., 1 (2025), 100010. https://doi.org/10.1016/j.scsadv.2025.100010 doi: 10.1016/j.scsadv.2025.100010
[9]	CCS, Key Trends in CCS Charger Development. 2025. Available from: https://www.accio.com/business/ccs2-charger-trends#:~:text=In%20June%202025%2C%20the%20U.S.%20and%20Canada%20deployed,total%20CCS%20ports%20compared%20to%20June%202024%202.
[10]	Y. Gong, X. Zhang, Research on the Global Industry Chain Layout of New Energy Vehicles and China's Status Enhancement, J. Changchun Financ. Coll., 177 (2024), 77–89.
[11]	McKinsey & Company, New twists in the electric-vehicle transition: A consumer perspective, 2025. Available from: https://www.mckinsey.com/features/mckinsey-center-for-future-mobility/our-insights/new-twists-in-the-electric-vehicle-transition-a-consumer-perspective
[12]	Z. Li, H. Fan, S. Dong, D. Liu, Green premium modeling based on total cost ownership: From the Chinese Electric Vehicles sales forecasting perspective, J. Cleaner Prod., 430 (2023), 139679. https://doi.org/10.1016/j.jclepro.2023.139679 doi: 10.1016/j.jclepro.2023.139679
[13]	D. Ouyang, Q. Zhang, X. Ou, Review of market surveys on consumer behavior of purchasing and using electric vehicle in China, Energy Procedia, 152 (2018), 612–617. https://doi.org/10.1016/j.egypro.2018.09.219 doi: 10.1016/j.egypro.2018.09.219
[14]	Z. Dong, Research on the Consumer Perception and Government Policies on Consumers' Purchase Intention of NEV in Sichuan, China, Learn. Educ., 10 (2021), 148–149. https://doi.org/10.18282/l-e.v10i3.2425 doi: 10.18282/l-e.v10i3.2425
[15]	X. Liu, F. Xie, H. Wang, C. Xue, The impact of policy mixes on new energy vehicle diffusion in China, Clean Technol. Environ. Policy, 23 (2021), 1457–1474. https://doi.org/10.1007/s10098-021-02040-z doi: 10.1007/s10098-021-02040-z
[16]	M. Hong, H. Wang, Research on customer opinion summarization using topic mining and deep neural network. Math. Comput. Simul., 185 (2021), 88–114. https://doi.org/10.1016/j.matcom.2020.12.009 doi: 10.1016/j.matcom.2020.12.009
[17]	Y. Liu, M. Zhang, X. Chen, K. Li, L. Tang, The impact of consumer sentiment on sales of new energy vehicles: Evidence from textual analysis. World Electr. Veh. J., 15 (2024), 318–337. https://doi.org/10.3390/wevj15070318 doi: 10.3390/wevj15070318
[18]	Y. Yang, Q. Li, C. Li, Q. Qin, User requirements analysis of new energy vehicles based on improved kano model, Energy, 309 (2024), 133134. https://doi.org/10.1016/j.energy.2024.133134 doi: 10.1016/j.energy.2024.133134
[19]	J. Cheah, S. Amaro, J. Roldan, Multigroup analysis of more than two groups in PLS-SEM: A review, illustration, and recommendations, J. Bus. Res., 156 (2023), 113539. https://doi.org/10.1016/j.jbusres.2022.113539 doi: 10.1016/j.jbusres.2022.113539
[20]	M. Hemat, F. Ghorbanian, A hybrid Kano-fuzzy AHP method for measuring customer satisfaction: A case study of transportation system, Manage. Sci. Lett., 1 (2011), 263–270. https://doi.org/10.5267/j.msl.2010.04.003 doi: 10.5267/j.msl.2010.04.003
[21]	Y. Bian, D. Shan, X. Yan, J. Zhang, New energy vehicle demand forecasting via an improved Bass model with perceived quality identified from online reviews, Ann. Oper. Res., 8 (2024), 1–9. https://doi.org/10.1007/s10479-024-06255-3 doi: 10.1007/s10479-024-06255-3
[22]	L. Zhang., H. Tong, Y. Liang, Q. Qin, Consumer purchase intention of new energy vehicles with an extended technology acceptance model: The role of attitudinal ambivalence, Transp. Res. Part A: Policy Pract., 174 (2023), 103742. https://doi.org/10.1016/j.tra.2023.103742 doi: 10.1016/j.tra.2023.103742
[23]	T. Jonas, G. Macht, Analyzing the urban-rural divide: Understanding geographic variations in charging behavior for a user-centered EVSE infrastructure, J. Transp. Geogr., 116 (2024), 103859. https://doi.org/10.1016/j.jtrangeo.2024.103859 doi: 10.1016/j.jtrangeo.2024.103859
[24]	Z. Zhang, N. Phakdeephirot, Factors Influencing Consumers' Behavior to Purchase New Energy Vehicles: Evidence from Zhengzhou city, China, Manage. Technol. Res. Commun., 2 (2025), No. 1. https://doi.org/10.21786/mntrc/2.1.1
[25]	J. Pang, J. Ye, X. Zhang, Factors influencing users' willingness to use new energy vehicles, PLOS ONE, 5 (2023), 315–343, https://doi.org/10.1371/journal.pone.0285815 doi: 10.1371/journal.pone.0285815
[26]	S. He, Y. Zhang, M. Tian, R. Li, K. Chen, A Study on the Product Demand of New Energy Vehicles Based on the Kano Model, J. Serv. Sci. Manage., 17 (2024), 464–477. https://doi.org/10.4236/jssm.2024.175026 doi: 10.4236/jssm.2024.175026
[27]	W. Wang, Z. Xie, M. Feng, Y. Qi, Y. Dou, Investigation of the Influencing Factors on Consumers' Purchase Willingness towards New-Energy Vehicles in China: A Questionnaire Analysis Using Matrix Model, Energies, 16 (2023), 5623. https://doi.org/10.3390/en16155623 doi: 10.3390/en16155623
[28]	R. Y. Fang, S. Xin, S. Zhang, G. Liu, X. Liu, et al., Regionally differentiated promotion of electric vehicles in China considering environmental and human health impacts, Environ. Res. Lett., 18 (2023), 1–34. https://doi.org/10.1088/1748-9326/acdbde doi: 10.1088/1748-9326/acdbde
[29]	Z. Lu, Z. Cai, Cueing roles of new energy vehicle manufacturers' technical capability and reputation in influencing purchase intention in China, Front. Energy Res., 10 (2022), 1–16. https://doi.org/10.3389/fenrg.2022.1032934 doi: 10.3389/fenrg.2022.1032934
[30]	X. Kang, S. Nagasawa, Integrating continuous fuzzy Kano model and fuzzy quality function deployment to the sustainable design of hybrid electric vehicle, J. Adv. Mech. Des. Sys. Manuf., 17 (2023), 1–17. https://doi.org/10.1299/jamdsm.2023jamdsm0019 doi: 10.1299/jamdsm.2023jamdsm0019
[31]	T. Zhao, Y. Zhang, M. Wang, W. Feng, S. Cao, Correction: A hybrid LSTM–transformer model for accurate remaining useful life prediction of lithium-ion batteries. Front. Electron., 6 (2025), 1–39. https://doi.org/10.3389/felec.2025.1693752 doi: 10.3389/felec.2025.1693752
[32]	A. Hussain, V. Eswarakrishnan, A. Aslam, S. Tripura, Charging stations demand forecasting using LSTM based hybrid transformer model, Sci. Rep., 15 (2025), 1–27. https://doi.org/10.1038/s41598-025-20421-y doi: 10.1038/s41598-025-20421-y
[33]	L. Shi, S. Ou, Y. Zhou, Y. Wu, X. Tan, Assessing Chinese user satisfaction with electric vehicle battery performance from online reviews, Transp. Res. Part D Transp. Environ., 141 (2025), 1–25. https://doi.org/10.1016/j.trd.2025.104644 doi: 10.1016/j.trd.2025.104644
[34]	H. Yu, Y. Li, W. Wang, Does the dual-credit policy promote the technological development of new energy vehicles? An industry chain reconstruction perspective, Heliyon, 10 (2024), 1–15. https://doi.org/10.1016/j.heliyon.2024.e31009 doi: 10.1016/j.heliyon.2024.e31009
[35]	I. Goodfellow, Deep Learning. MIT Press, 2016. Available from: https://mitpress.mit.edu/9780262035613/deep-learning/.
[36]	B. Rahman, Maryani, Optimizing Customer Satisfaction Through Sentiment Analysis: A BERT-Based Machine Learning Approach to Extract Insights, IEEE Access, 12 (2024), 151476–151489. https://doi.org/10.1109/ACCESS.2024.3478835 doi: 10.1109/ACCESS.2024.3478835
[37]	J. Zeng, T. Liu, R. Feiock, F. Li, The impacts of China's provincial energy policies on major air pollutants: A spatial econometric analysis, Energy Policy, 132 (2019), 392–403. https://doi.org/10.1016/j.enpol.2019.05.052 doi: 10.1016/j.enpol.2019.05.052
[38]	C. Yan, D. Wang, Digitalization and green innovation: a fuzzy-set qualitative comparative analysis based on 30 provinces in China, Chin. Manage. Stud., 19 (2025), 1852–1872. https://doi.org/10.1108/CMS-05-2024-0302 doi: 10.1108/CMS-05-2024-0302
[39]	G. Jin, Z. Huang, Asymmetric impact of renewable electricity consumption and industrialization on environmental sustainability: Evidence through the lens of load capacity factor, Renewable Energy, 212 (2023), 514–522. https://doi.org/10.1016/j.renene.2023.05.045 doi: 10.1016/j.renene.2023.05.045
[40]	DiLink 4.0 User Behavior Report. BYD Auto, 2025. Available from: https://www.byd.com/en-jo/support/dilink.
[41]	Battery Day 2024 Technical Whitepaper. Tesla Inc, 2024. Available from: https://www.tesmanian.com/blogs/tesmanian-blog/tesla-battery-day-is-the-final-nail-in-the-coffin-for-ice-vehicles.
[42]	A. Alawi, A. Saeed, M. Sharqawy, M. Janaideh, A Comprehensive Review of Thermal Management Challenges and Safety Considerations in Lithium-Ion Batteries for Electric Vehicles, Batteries, 11 (2025), 1–49. https://doi.org/10.3390/batteries11070275 doi: 10.3390/batteries11070275
[43]	X. Feng, B. Huang, Y. Li, R&D investment in new energy vehicles with purchase subsidy based on technology adoption life cycle and customers' choice behaviour, IET Intel. Transport Syst., 14 (2020), 1371–1377. https://doi.org/10.1049/iet-its.2019.0649 doi: 10.1049/iet-its.2019.0649

jimo-22-03-047-s001.pdf

Reader Comments

Your name:*

Email:*
© 2026 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)