The first-launch economy has emerged as a critical policy instrument for driving industrial upgrading and rural revitalization in China’s underdeveloped regions; however, quantitative frameworks to assess its industrial performance remain limited. This study proposes a novel digital-intelligence-driven framework to evaluate and forecast production expansion dynamics, utilizing the plush toy industry in Ankang City (2018-2026) as a representative longitudinal case study. Based on the integration of multi-source data from the National Bureau of Statistics, e-commerce platforms, and web-crawled records, a robust Extract-Transform-Load (ETL) pipeline is constructed. This process employed systematic time-series standardization and exhaustive aggregation to generate a monthly production value of industrial activity. To capture complex non-linear trends, a Long Short-Term Memory (LSTM) neural network was developed to model efficiency evolution, incorporating the national export benchmark of toys as an exogenous variable. In this study, model performance was validated using the coefficient of determination (R2), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Mean Bias Error (MBE), demonstrating high predictive fidelity. As the first-launched industry, analytical results in this study reveal a sustained efficiency trajectory in Ankang’s plush toy sector post-2018, providing quantitative evidence of the efficacy of digital-intelligence-enabled interventions. The findings in this study offer a transferable, data-driven methodology for the following studies to monitor emerging regional industries and optimize resource allocation within the first-launch economy model.
References
[1]
Adamopoulos, I., Valamontes, A., Karantonis, J. T., Tropaitis, P. P., & Syrou, N. (2025). Enhancing Economic Growth Time Series for UAE Forecasting with Deep Learning: A Seq2Seq and Attention-Driven LSTM Approach. EDRAAK, 2025, 62-75. https://doi.org/10.70470/edraak/2025/009
[2]
Ankang Plush Toy Industry Inspection Group (2018). Investigation Report on the Plush Toy Industry. Xinhua News Agency. https://www.ankang.gov.cn/Content-1537332.html
[3]
Cen, T., Lin, S., & Wu, Q. (2022). How Does Digital Economy Affect Rural Revitalization? The Mediating Effect of Industrial Upgrading. Sustainability, 14, Article No. 16987. https://doi.org/10.3390/su142416987
[4]
Chen, D., Wei, W., Hu, D., & Muralidharan, E. (2016). Survival Strategy of OEM Companies: A Case Study of the Chinese Toy Industry. International Journal of Operations & Production Management, 36, 1065-1088. https://doi.org/10.1108/ijopm-04-2015-0212
[5]
Deng, X., Huang, M., & Peng, R. (2024). The Impact of Digital Economy on Rural Revitalization: Evidence from Guangdong, China. Heliyon, 10, e28216. https://doi.org/10.1016/j.heliyon.2024.e28216
[6]
Department of Human Resources, & Social Security of Shaanxi Province (2025). Ankang: Systematically Building a New Integrated Development Paradigm of “Plush Toys + AI + Cultural Tourism”. https://rst.shaanxi.gov.cn/sy/ztzl/rdzt/rsgzjyq/jyjl/202512/t20251231_3601171.html
[7]
Fawaz, H. I., Forestier, G., Weber, J., Idoumghar, L., & Muller, P. A. (2018). Data Augmentation Using Synthetic Data for Time Series Classification with Deep Residual Networks.
[8]
Fritsch, F. N., & Carlson, R. E. (1980). Monotone Piecewise Cubic Interpolation. SIAM Journal on Numerical Analysis, 17, 238-246. https://doi.org/10.1137/0717021
[9]
Gal, Y., & Ghahramani, Z. (2016). Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning. In International Conference on Machine Learning (pp. 1050-1059). PMLR.
[10]
Gereffi, G. (2019). Global Value Chains, Development, and Emerging Economies. In P. Lund-Thomsen, et al. (Eds.), Business and Development Studies (pp. 125-158). Routledge. https://doi.org/10.4324/9781315163338-6
[11]
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
[12]
Greff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J. (2016). LSTM: A Search Space Odyssey. IEEE Transactions on Neural Networks and Learning Systems, 28, 2222-2232. https://doi.org/10.1109/tnnls.2016.2582924
[13]
Haider, S. A., Naqvi, S. R., Akram, T., Umar, G. A., Shahzad, A., Sial, M. R. et al. (2019). LSTM Neural Network Based Forecasting Model for Wheat Production in Pakistan. Agronomy, 9, Article No. 72. https://doi.org/10.3390/agronomy9020072
[14]
Hamiane, S., Ghanou, Y., Khalifi, H., & Telmem, M. (2024). Comparative Analysis of LSTM, ARIMA, and Hybrid Models for Forecasting Future GDP. Ingénierie des Systèmes d Information, 29, 853-861. https://doi.org/10.18280/isi.290306
[15]
Hochreiter, S., & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
[16]
Hong, Y., & Liang J. (2023). Plush Toys Produced in Small City in NW China’s Shaanxi Reach over 80 Countries, Regions. People’s Daily. https://en.people.cn/n3/2023/0921/c98649-20074698.html
[17]
Hyndman, R. J., & Athanasopoulos, G. (2018). Forecasting: Principles and Practice. OTexts.
[18]
Iwana, B. K., & Uchida, S. (2021). An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks. PLOS ONE, 16, e0254841. https://doi.org/10.1371/journal.pone.0254841
[19]
Kaplinsky, R., & Morris, M. (2016). Thinning and Thickening: Productive Sector Policies in the Era of Global Value Chains. The European Journal of Development Research, 28, 625-645. https://doi.org/10.1057/ejdr.2015.29
[20]
Kee, H. L., & Tang, H. (2016). Domestic Value Added in Exports: Theory and Firm Evidence from China. American Economic Review, 106, 1402-1436. https://doi.org/10.1257/aer.20131687
[21]
Liu, Z., Wu, H., & Badar, I. H. (2024a). Impact of Rural Digital Economy Development on Rural Revitalisation—Evidence from China. Sustainability, 16, Article No. 4573. https://doi.org/10.3390/su16114573
[22]
Liu, F., Yu, Z. C., & Deng, M. L. (2024b). An Empirical Study on the Impact of Digital Economy Development on the Quality of Rural Revitalization. Science & Technology Progress and Policy, 41, 47-57.
[23]
Liu, Y. (2019). Event and Sustainable Culture-Led Regeneration: Lessons from the 2008 European Capital of Culture, Liverpool. Sustainability, 11, Article No. 1869. https://doi.org/10.3390/su11071869
[24]
Lu, Y., Meng, Y., Chen, L., & Zhang, Y. (2024). Can the Digital Economy Contribute to Rural Revitalization? A Case of from China? PLOS ONE, 19, e0310313. https://doi.org/10.1371/journal.pone.0310313
[25]
Luo, G., Yang, Y., & Wang, L. (2023). Driving Rural Industry Revitalization in the Digital Economy Era: Exploring Strategies and Pathways in China. PLOS ONE, 18, e0292241. https://doi.org/10.1371/journal.pone.0292241
[26]
Pascanu, R., Mikolov, T., & Bengio, Y. (2013). On the Difficulty of Training Recurrent Neural Networks. In International Conference on Machine Learning (pp. 1310-1318). PMLR.
[27]
Paszkowski, S., & Sarniak, ？. (2019). Differences in Rural Development Potential across Polish Regions. Journal of Agribusiness and Rural Development, 51, 59-68. https://doi.org/10.17306/j.jard.2019.01102
[28]
Pyo, D. J. (2025). Enhancing GDP Growth Forecasting with LSTM, GRU, and Hybrid Model: Evidence from South Korea. Sage Open, 15, No. 3. https://doi.org/10.1177/21582440251359828
[29]
Shi, M., Yuan, H. T., & Chen, X. A. (2026). Digital-Intelligence Empowerment for Rural Revitalization: Estimating First-Launch Economy Productivity Efficiency via ETL-MLP Time-Series Reconstruction. Open Journal of Social Sciences, 14, 340-367. https://doi.org/10.4236/jss.2026.143020
[30]
Siami-Namini, S., & Namin, A. S. (2018). Forecasting Economics and Financial Time Series: ARIMA vs. LSTM. https://arxiv.org/abs/1803.06386
[31]
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A Simple Way to Prevent Neural Networks from Overfitting. Journal of Machine Learning Research, 15, 1929-1958.
[32]
Tian, Y., Liu, Q., Ye, Y., Zhang, Z., & Khanal, R. (2023). How the Rural Digital Economy Drives Rural Industrial Revitalization—Case Study of China’s 30 Provinces. Sustainability, 15, Article No. 6923. https://doi.org/10.3390/su15086923
[33]
Wang, S., Peng, T., Du, A. M., & Lin, X. (2025). The Impact of the Digital Economy on Rural Industrial Revitalization. Research in International Business and Finance, 76, Article ID: 102878. https://doi.org/10.1016/j.ribaf.2025.102878
[34]
Wang, Y., Peng, Q., Jin, C., Ren, J., Fu, Y., & Yue, X. (2023). Whether the Digital Economy Will Successfully Encourage the Integration of Urban and Rural Development: A Case Study in China. Chinese Journal of Population, Resources and Environment, 21, 13-25. https://doi.org/10.1016/j.cjpre.2023.03.002
[35]
Xu, Q. (2024). Toys Help Ankang Residents to Lead a Plush New Life. China Daily. https://www.chinadailyhk.com/hk/article/232819?utm
[36]
Yu, H. C. (2023). Economic Watch: Made-in-China Stuffed Bears Spread Joy of Christmas Overseas. Xinhua News Agency. https://eng.yidaiyilu.gov.cn/p/0M6INNO1.html
[37]
Zhang, T. (2024). How Small Toys Form Large Industrial Clusters (Onsite Commentary)—Acting as Steadfast Practitioners and Doers in Advancing Chinese-Style Modernization. People’s Daily. https://cpc.people.com.cn/BIG5/n1/2024/0509/c64387-40231976.html
[38]
Zhang, Z., Sun, C., & Wang, J. (2023). How Can the Digital Economy Promote the Integration of Rural Industries—Taking China as an Example. Agriculture, 13, Article No. 2023. https://doi.org/10.3390/agriculture13102023
[39]
Zheng, C., & Li, H. (2023). The Prediction of Collective Economic Development Based on the PSO-LSTM Model in Smart Agriculture. PeerJ Computer Science, 9, e1304. https://doi.org/10.7717/peerj-cs.1304
[40]
Zou, L. (2025). Proposal on Further Advancing the Upgrading and Development of the Plush Toy Industry. Ankang Municipal People’s Congress. https://rd.ankang.gov.cn/Content-2874919.html
