Huihui Song
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Huihui Song has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Qiang Li
School of Economics and Management, Shanghai Technical Institute of Electronics & Information, Shanghai, China
4 shared publications - Fei Yin
School of Economics and Management, Shanghai Technical Institute of Electronics & Information, Shanghai, China
1 shared publication - Peng Hou
School of Finance and Taxation, Zhengzhou Technology and Business University, Zhengzhou, Henan, China
1 shared publication - Wen Lu
School of Economics and Management, Shanghai Technical Institute of Electronics & Information, Shanghai, China
1 shared publication - Yongmei Liang
Student Work Department, Shanghai Technical Institute of Electronics & Information, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 27 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 81-88
Research on Evolution Simulation of FinTech Talent Demand and Precision Industry-Education Integration Based on C-TimeGAN
- 27 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 81-88
Open AccessResearch on Evolution Simulation of FinTech Talent Demand and Precision Industry-Education Integration Based on C-TimeGAN
- Open Access
- 19 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1079-1084
Random Forest Analysis of Digital Finance for Community Governance and Resident Well-being
The rapid integration of digital finance into community ecosystems has become a pivotal force for modernizing governance, yet existing research remains predominantly qualitative and lacks quantitative evidence to disentangle the complex mechanisms driving residents' well-being. To address this gap, this study empirically investigates the multidimensional impact of digital finance factors including accessibility, civic participation, credit governance, and financial literacy on community governance efficacy and residents' subjective well-being. Utilizing a dataset of 247 community residents, we employed a Random Forest Regressor, a robust ensemble machine learning algorithm, to model non-linear interactions and identify critical determinants. The experimental results demonstrate the exceptional predictive capability of the model, achieving a Coefficient of Determination of 0.98 and a Root Mean Squared Error of 0.15. Crucially, feature importance analysis reveals that the fairness of credit evaluation standards is the paramount driver of well-being with an importance score exceeding 0.47, significantly outweighing technical accessibility, while financial literacy emerges as a secondary critical factor reinforced by the synergistic effect between digital access and civic engagement. These findings provide novel data-driven insights suggesting that to maximize governance outcomes, policymakers must prioritize procedural justice and knowledge empowerment over mere infrastructure expansion.
- 19 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1079-1084
Open AccessRandom Forest Analysis of Digital Finance for Community Governance and Resident Well-being
The rapid integration of digital finance into community ecosystems has become a pivotal force for modernizing governance, yet existing research remains predominantly qualitative and lacks quantitative evidence to disentangle the complex mechanisms driving residents' well-being. To address this gap, this study empirically investigates the multidimensional impact of digital finance factors including accessibility, civic participation, credit governance, and financial literacy on community governance efficacy and residents' subjective well-being. Utilizing a dataset of 247 community residents, we employed a Random Forest Regressor, a robust ensemble machine learning algorithm, to model non-linear interactions and identify critical determinants. The experimental results demonstrate the exceptional predictive capability of the model, achieving a Coefficient of Determination of 0.98 and a Root Mean Squared Error of 0.15. Crucially, feature importance analysis reveals that the fairness of credit evaluation standards is the paramount driver of well-being with an importance score exceeding 0.47, significantly outweighing technical accessibility, while financial literacy emerges as a secondary critical factor reinforced by the synergistic effect between digital access and civic engagement. These findings provide novel data-driven insights suggesting that to maximize governance outcomes, policymakers must prioritize procedural justice and knowledge empowerment over mere infrastructure expansion.
- Open Access
- 18 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 8-14
Addressing Digital Finance Challenges: The Application and Op-timization of Logistic Regression Models in Fraud Detection Sys-tems
- 18 April 2025
- Published by Association for Computing Machinery (ACM)
- p. 8-14
Open AccessAddressing Digital Finance Challenges: The Application and Op-timization of Logistic Regression Models in Fraud Detection Sys-tems
- Open Access
- 14 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 282-288
Employee Performance Prediction Model Based on BP Neural Networks
- 14 March 2025
- Published by Association for Computing Machinery (ACM)
- p. 282-288
Open AccessEmployee Performance Prediction Model Based on BP Neural Networks