Financing Mechanisms and Preferences of Technology-Driven Small- and Medium-Sized Enterprises in the Digitalization Context
In the context of digitalization, this study investigated the financing mechanisms and preferences of technology-driven small and medium-sized enterprises (TDSMEs) listed on the National Equities Exchange and Quotations (NEEQ) in China. Its primary objective was to identify the factors influencing f...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Systems |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-8954/13/2/68 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In the context of digitalization, this study investigated the financing mechanisms and preferences of technology-driven small and medium-sized enterprises (TDSMEs) listed on the National Equities Exchange and Quotations (NEEQ) in China. Its primary objective was to identify the factors influencing financing decisions and to elucidate how TDSMEs choose their financing options in a rapidly evolving digital environment. To achieve this goal, we constructed a panel regression model using financial data from 41 TDSMEs (2017–2023), identifying the key determinants of financing decisions while examining the impact of regional heterogeneity and validating the model’s robustness. The empirical findings indicated that various independent variables, including a firm’s capital structure, significantly influenced both internal and external financing. Additionally, six machine learning (ML) algorithms were employed to predict financing preferences. Among them, the random forest (RF) model achieved the best financing preferences performance, with an average F1 score of 0.814, indicating its robust predictive capability for TDSMEs’ financing preferences. To further validate the proposed models, we conducted a case study on a TDSME newly recognized in 2024 (named TS Pharmaceutical). Both the Lasso and RF models demonstrated outstanding predictive accuracy, confirming the practicality of the ML models. These results provide valuable insights into navigating the ever-changing digital financing landscape, offering recommendations for policymakers and financial institutions to better support TDSMEs. The key innovation of this study lies in its novel integration of conventional panel regression analysis and ML techniques, thereby bridging the gap between digital transformation and financing strategies while contributing both theoretically and practically to the field. |
|---|---|
| ISSN: | 2079-8954 |