Design and Study of Zombie Enterprise Classification and Recognition Systems Based on Ensemble Learning
The existence of a large number of zombie enterprises will affect the economic development and hinder the transformation and upgrading of economic industries. To improve the accuracy of zombie enterprise identification, this paper takes multidimensional enterprise data as the original data set, divides it into training set and validation set, and gives the corresponding data pre-processing methods. Combined with 14 standardized features, an integrated learning model for zombie enterprise classification and recognition is constructed and studied based on three pattern recognition algorithms. By using the idea of integration and the cross-validation method to determine the optimal parameters, the Gradient Boosting Decision Tree (GBDT), linear kernel Support Vector Machine (SVM) and Deep Neural Network (DNN) algorithms with classification accuracies of 95%, 96% and 96%, respectively, are used as sub-models, and a more comprehensive strong supervision model with a classification accuracy of 98% is obtained by the stacking method in combination with the advantages of multiple sub- models to analyze the fundamental information of 30885 enterprises. The study improves the accuracy of zombie enterprise identification to 98%, builds enterprise portraits based on this, and finally visualizes the classification results through the platform, which provides an auxiliary means for zombie enterprise classification and identification.
[1] Bargagli-Dtoffi F., Riccaboni M., and Rungi A., “Machine Learning for Zombie Hunting. Firms Failures and Financial Constraints,” Working Papers, 2020.
[2] Jiliang C., “Research on the Influence of Zombie Enterprises on Resource Allocation in China,” Shenzhen University, 2019.
[3] Juan H., Weifeng Z., Wei F., and Heng Z., “Study on the Prediction Model of Albacore Tuna Fishing Ground in the South Pacific Based on Ensemble Learning,” Southern Fisheries Science, vol. 16， no. 5, pp. 194-200, 2020. doi: 10.12131/20200022
[4] Juan T., Dingju Z., and Wenhan Y., “Research on Enterprise Portraits Based on Big Data Platforms,” Computer Science, vol. 45, no. S2, pp. 58-62, 2018.
[5] Kane E., “Dangers of Capital Tolerance: The Case of the FSLIC and Zombie S&Ls,” Contemporary Economic Policy, vol. 05, no. 1, pp. 77-83, 1987. DOI: 10.1111/j.1465-7287.1987.tb00247.x
[6] Qin W. and Tan S., “Zombie Enterprise Characteristics, Causes and Identification Disposal Suggestions,” Finance and Economy, vol. 04, pp. 93-119, 2019.
[7] Shaoqing H. and Yan C., “The Distribution Features and Classified Disposition of China’s Zombie Firms,” China's Industrial Economy, vol. 03, pp. 24-43, 2017.
[8] Wang H. and Changgang L., “Application of Stacking Integrated Learning Method in Sales Forecasting,” Computer Applications and Software, vol. 37, no. 8, pp. 85-90， 2020. DOI: 10.3969/j.issn.1000-386x.2020.08.016
[9] Xiaoyan L., “Research on Recognition of Chinese Zombie Enterprise under Supply-Side Reform,” Economic Restructuring, vol. 03, pp: 194-200, 2019.
[10] Xiaoyang L. and Qiang Q., “China’s Zombie Firms: Identification and Classification,” International Financial Research, vol. 08, pp. 3- 13, 2017.
[11] Yuping J., Cheng Y., Yanrong L., Haiyan S., Di L., Jiang Z., Hao W., and Hao C., “An Early Screening Method of Chronic Kidney Disease Based on Ensemble Learning Algorithm,” Journal of Southwest University (Natural Science Edition), vol. 42, no. 10, pp, 17-24, 2020.
[12] Yu S., Zhali L., and Xuewen L., “Ensemble Learning and Feature Integration in Prediction for College Students Grant,” Journal of Xi'an University of Science and Technology, vol. 40， no. 4, pp. 744-750, 2020. 10.13800/j.cnki.xakjdxxb.2020.0424
[13] Zheng J., Qin L., Liu K., Tian B., Tian C., Li B., Chen G., “Django: Bilateral Coflow Scheduling with Predictive Concurrent Connections,” Journal of Parallel and Distributed Computing, vol. 152, pp. 45-56, 2021. https://doi.org/10.1016/j.jpdc.2021.01.006
[14] Zhihua Z., “Machine Learning,” Tsinghua University Press, Beijing, 2016.