Research on Accounting Information Quality Evaluation Model of Listed Companies from the Perspective of Differentiated Machine Learning
World Scientific Research Journal, (2026), Vol.12, No.10, pp.91-101
Published: September 17, 2026
Abstract
Developing quantitative tools to evaluate the accounting information quality of listed companies is of great value for in- vestors' risk prevention. Based on the selection of multi-dimensional factors affecting the accounting information quality , the random forest model is used to screen the importance , and then the accounting information quality evaluation system is built. At the same time , based on convolutional neural netowrk long short-term memory (CNN-LSTM) method , the evaluation model of accounting information quality is constructed , and the good performance of the model in the evaluation of accounting informa- tion quality is proved.
Keywords:
Listed company; accounting information quality; random forest; convolutional neural network; long short-term memory network.
APA Citation:
Peitian Su, Hongtao Rong, Guo Xiang, Danfeng Huang (2026). Research on Accounting Information Quality Evaluation Model of Listed Companies from the Perspective of Differentiated Machine Learning. World Scientific Research Journal, 12(10), 91-101. https://doi.org/10.6911/WSRJ.202610_12(10).0009
References
- Chen, Z. (2019). Research on General Secretary Xi Jinping's important discourses on the construction of the capital market. Securities Market Herald, (4), 4–12.
- Sun, F., & Zheng, J. (2018). Research on intelligent evaluation of accounting information quality of listed companies based on "Internet+". Accounting Research, (3), 86–90.
- Li, Q., & Ma, Z. H. (2022). Research on the construction, evaluation and early warning of accounting information quality index. Mathematical Statistics and Management, 41(4), 749–760.
- Fei, Y. (2023). Research on accounting information quality and financing dilemma of operating enterprises. Modern Economic Exploration, (1), 84–92.
- Geng, C. (2019). Accounting information quality evaluation based on BP neural network. Accounting Communication, (31), 107–111.
- Huang, H. P., & Song, S. J. (2012). Internal control report and accounting information quality and enterprise value: An empirical study based on A-share market in Shanghai. Journal of Economics and Management, 34(1), 122–128.
- Yu, J. F., He, Y. L., Wu, H. H., et al. (2022). Design of power distribution network outage prediction scheme based on random forest algorithm. Microcomputer Application, 38(12), 76–79.
- Wang, X., Wang, T., Ma, Y., et al. (2021). Credit risk assessment method for P2P online lending borrowers based on deep forest. Computer Science, 48(S2), 429–434.
- Yu, Y., Si, X. S., Hu, C. H., et al. (2019). A review of recurrent neural networks: LSTM cells and network architectures. Neural Computation, 31(7), 1235–1270.
- Zhang, S., Zhou, X., Zhang, Y., et al. (2023). Research on electricity consumption prediction technology for smart homes based on CNN encoding-LSTM decoding hybrid neural network. Microcomputer Application, 39(1), 1–3.
- Li, M., Ning, D., & Guo, J. (2019). A CNN-LSTM model based on the attention mechanism and its application. Computer Engineering and Applications, 55(13), 20–27.
- Zhao, Q., & Yu, Y. (2022). Detection of electric current in living organisms based on long-term and short-term memory neural networks. Sensors and Microsystems, 41(1), 142–145.
- Zhou, J. Y., & Zeng, X. H. (2022). Deep learning model based on regularization constrained meta-learning optimizer. Computer Applications and Software, 39(10), 266–273.