Lingbing Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lingbing Feng has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Yanlin Shi
Macquarie University
5 shared publications - Tong Fu
City University of Macau Taipa Macau
4 shared publications Ali M. Kutan
3 shared publications- Dasen Huang
School of Digital Economics Jiangxi University of Finance and Economics Nanchang Jiangxi China
3 shared publications - Alan H. Welsh
Research School of Finance, Actuarial Studies and Statistics, The Australian National University, Canberra, Australia
2 shared publications - Haochen Li2 shared publications
Latest Publications
- 5 October 2026
- Published by Elsevier in Technovation
- Vol. 158
Corporate innovation propensity: From measurement to impact—A text-based analytical approach
- 5 October 2026
- Published by Elsevier in Technovation
- Vol. 158
Corporate innovation propensity: From measurement to impact—A text-based analytical approach
- Open Access
- 31 August 2026
- Published by World Scientific Pub Co Pte Ltd in Journal of Transition Economics and Finance
- Vol. 02 (03)
National Big Data Comprehensive Pilot Zone Policy and Corporate AI Innovation Output: Evidence from Chinese A-Share Listed Companies
Using the establishment of National Big Data Comprehensive Pilot Zones as a quasi-natural experiment, this paper examines the impact of the pilot-zone policy on corporate AI innovation output based on Chinese A-share listed companies from 2012 to 2024 and a difference-in-differences design. The dependent variable is constructed from the CNRDS listed-firm AI patent application database and measured by the natural logarithm of one plus the number of AI invention patent applications independently filed by a firm in a given year. The results show that the policy significantly increases corporate AI innovation output. The conclusion remains valid after the parallel-trend test, placebo test, PSM-DID test, and a series of robustness checks. Mechanism-clue tests provide evidence consistent with two possible channels: alleviation of financing constraints and higher AI textual attention. Heterogeneity analysis further shows that the policy effect is more pronounced among firms located in regions with larger R&D personnel pools, firms with higher financing constraints, and state-owned enterprises, and the corresponding between-group differences are statistically significant. From the perspectives of transition economics, factor market reform, and transaction costs, this paper explains the micro-level innovation effect of digital policy and provides empirical evidence for understanding how data-factor marketization affects corporate AI innovation.
- 31 August 2026
- Published by World Scientific Pub Co Pte Ltd in Journal of Transition Economics and Finance
- Vol. 02 (03)
Open AccessNational Big Data Comprehensive Pilot Zone Policy and Corporate AI Innovation Output: Evidence from Chinese A-Share Listed Companies
Using the establishment of National Big Data Comprehensive Pilot Zones as a quasi-natural experiment, this paper examines the impact of the pilot-zone policy on corporate AI innovation output based on Chinese A-share listed companies from 2012 to 2024 and a difference-in-differences design. The dependent variable is constructed from the CNRDS listed-firm AI patent application database and measured by the natural logarithm of one plus the number of AI invention patent applications independently filed by a firm in a given year. The results show that the policy significantly increases corporate AI innovation output. The conclusion remains valid after the parallel-trend test, placebo test, PSM-DID test, and a series of robustness checks. Mechanism-clue tests provide evidence consistent with two possible channels: alleviation of financing constraints and higher AI textual attention. Heterogeneity analysis further shows that the policy effect is more pronounced among firms located in regions with larger R&D personnel pools, firms with higher financing constraints, and state-owned enterprises, and the corresponding between-group differences are statistically significant. From the perspectives of transition economics, factor market reform, and transaction costs, this paper explains the micro-level innovation effect of digital policy and provides empirical evidence for understanding how data-factor marketization affects corporate AI innovation.
- 19 August 2026
- Published by Wiley in Managerial and Decision Economics
- Vol. 47 (8) , 1931-1932
Compelling Empirical Research
- 19 August 2026
- Published by Wiley in Managerial and Decision Economics
- Vol. 47 (8) , 1931-1932
Compelling Empirical Research
- Open Access
- 20 May 2026
- Published by Elsevier in SSRN Electronic Journal
Capturing Time-Varying Uncertainty: Does HyperparameterRetuning Frequency Matter? Evidence from China's High-Frequency Data
Accurate volatility forecasting is important for understanding market uncertainty, risk formation, and portfolio decisions in China’s equity market. This paper examines whether the frequency of hyperparameter retuning influences rolling machine-learning forecasts of realized volatility. Using 5-minute high-frequency data for the CSI 300 Index, we develop a dynamic forecasting framework with Bayesian optimization and compare linear benchmarks, shrinkage methods, and gradient-boosted regression tree models under daily, weekly, monthly, and quarterly retuning schedules. China provides a useful institutional setting for this analysis because substantial retail participation, policy-sensitive information flows, and trading frictions can make volatility dynamics both adaptive and noisy. We interpret retuning frequency as a practical learning-speed choice: more frequent retuning may help models respond to changing market conditions, but it may also increase sensitivity to short-lived noise; less frequent retuning may improve stability, but may delay adaptation to shifts in the volatility process. The results reveal a non-monotonic frequency–performance pattern. In the baseline CSI 300 setting, weekly retuning often performs well for several gradient-boosted tree models, although the preferred frequency varies across model classes, evaluation windows, and volatility regimes. TreeSHAP analysis indicates that option-implied uncertainty, downside realized variation, and investor-attention-related signals are important predictors. Overall, the findings suggest that retuning frequency is a relevant design choice in machine-learning volatility forecasting for noisy and institutionally distinctive emerging markets.
- 20 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCapturing Time-Varying Uncertainty: Does HyperparameterRetuning Frequency Matter? Evidence from China's High-Frequency Data
Accurate volatility forecasting is important for understanding market uncertainty, risk formation, and portfolio decisions in China’s equity market. This paper examines whether the frequency of hyperparameter retuning influences rolling machine-learning forecasts of realized volatility. Using 5-minute high-frequency data for the CSI 300 Index, we develop a dynamic forecasting framework with Bayesian optimization and compare linear benchmarks, shrinkage methods, and gradient-boosted regression tree models under daily, weekly, monthly, and quarterly retuning schedules. China provides a useful institutional setting for this analysis because substantial retail participation, policy-sensitive information flows, and trading frictions can make volatility dynamics both adaptive and noisy. We interpret retuning frequency as a practical learning-speed choice: more frequent retuning may help models respond to changing market conditions, but it may also increase sensitivity to short-lived noise; less frequent retuning may improve stability, but may delay adaptation to shifts in the volatility process. The results reveal a non-monotonic frequency–performance pattern. In the baseline CSI 300 setting, weekly retuning often performs well for several gradient-boosted tree models, although the preferred frequency varies across model classes, evaluation windows, and volatility regimes. TreeSHAP analysis indicates that option-implied uncertainty, downside realized variation, and investor-attention-related signals are important predictors. Overall, the findings suggest that retuning frequency is a relevant design choice in machine-learning volatility forecasting for noisy and institutionally distinctive emerging markets.
- Open Access
- 15 May 2026
- Published by Elsevier in SSRN Electronic Journal
Information Frictions, Data Factor Agglomeration, and Cross-Regional Corporate Investment
This paper examines whether data factor agglomeration promotes cross-regional corporate investment by reducing information frictions. Using a firm–destination–year panel of Chinese listed firms from 2010 to 2022, we exploit regional variation generated by the rollout of National Big Data Comprehensive Pilot Zones to identify the effect of data factor agglomeration on cross-regional corporate investment. The results show that data factor agglomeration significantly increases firms' investment in non-local destinations, suggesting that data-related institutions can facilitate spatial capital mobility. Mechanism analyses suggest that the effect operates through lower financing constraints, higher operating efficiency, and a more competitive market environment. The effect is stronger for non-state-owned firms, smaller-scale investments, and firms with higher digital dependence. These findings highlight the role of data-related institutional reforms in reducing spatial information frictions and shaping the geography of corporate investment.
- 15 May 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessInformation Frictions, Data Factor Agglomeration, and Cross-Regional Corporate Investment
This paper examines whether data factor agglomeration promotes cross-regional corporate investment by reducing information frictions. Using a firm–destination–year panel of Chinese listed firms from 2010 to 2022, we exploit regional variation generated by the rollout of National Big Data Comprehensive Pilot Zones to identify the effect of data factor agglomeration on cross-regional corporate investment. The results show that data factor agglomeration significantly increases firms' investment in non-local destinations, suggesting that data-related institutions can facilitate spatial capital mobility. Mechanism analyses suggest that the effect operates through lower financing constraints, higher operating efficiency, and a more competitive market environment. The effect is stronger for non-state-owned firms, smaller-scale investments, and firms with higher digital dependence. These findings highlight the role of data-related institutional reforms in reducing spatial information frictions and shaping the geography of corporate investment.
- 31 July 2025
- Published by Wiley in Managerial and Decision Economics
- Vol. 46 (8) , 4232-4252
Administrative Reforms and Enterprise Digital Transformation in China: Mechanisms and Impacts
This study examines the relationship between the “Revoke County to Urban District” (CTD) policy and the digital transformation (DT) of local enterprises in China, using panel data from A‐share listed companies from 2003 to 2020. By leveraging the CTD policy as a quasi‐natural experiment, a time‐varying difference‐in‐differences (DID) model is employed, supplemented by robustness checks using propensity score matching (PSM‐DID) and a generalized random forest (GRF) model. The findings reveal that the CTD policy significantly enhances enterprise DT, with the effect being more pronounced in non–state‐owned enterprises, non–high‐tech industries, county‐level cities, and regions with high levels of urbanization and digital financial inclusion. Furthermore, a GRF‐based conditional average treatment effect (CATE) analysis explores the interplay of firm characteristics—fixed asset proportion, gearing ratio, and return on assets—on the policy impact. The study identifies three core mechanisms driving DT: optimized resource allocation, improved internal controls, and enhanced human capital. These insights not only offer a theoretical framework for understanding the localized implementation of administrative reforms in China but also provide practical recommendations for designing policies to foster digital transformation.
- 31 July 2025
- Published by Wiley in Managerial and Decision Economics
- Vol. 46 (8) , 4232-4252
Administrative Reforms and Enterprise Digital Transformation in China: Mechanisms and Impacts
This study examines the relationship between the “Revoke County to Urban District” (CTD) policy and the digital transformation (DT) of local enterprises in China, using panel data from A‐share listed companies from 2003 to 2020. By leveraging the CTD policy as a quasi‐natural experiment, a time‐varying difference‐in‐differences (DID) model is employed, supplemented by robustness checks using propensity score matching (PSM‐DID) and a generalized random forest (GRF) model. The findings reveal that the CTD policy significantly enhances enterprise DT, with the effect being more pronounced in non–state‐owned enterprises, non–high‐tech industries, county‐level cities, and regions with high levels of urbanization and digital financial inclusion. Furthermore, a GRF‐based conditional average treatment effect (CATE) analysis explores the interplay of firm characteristics—fixed asset proportion, gearing ratio, and return on assets—on the policy impact. The study identifies three core mechanisms driving DT: optimized resource allocation, improved internal controls, and enhanced human capital. These insights not only offer a theoretical framework for understanding the localized implementation of administrative reforms in China but also provide practical recommendations for designing policies to foster digital transformation.
- Open Access
- 29 July 2025
- Published by Elsevier in Borsa Istanbul Review
- Vol. 25 (6) , 1337-1347
How does local government debt expansion affect firm value in China?
- 29 July 2025
- Published by Elsevier in Borsa Istanbul Review
- Vol. 25 (6) , 1337-1347
Open AccessHow does local government debt expansion affect firm value in China?
- 9 May 2025
- Published by Emerald Publishing in Journal of Accounting Literature
- Vol. ahead-of-p (ahead-of-p)
The impact of large language models on accounting and future application scenarios
Purpose: This paper examines the transformative impact of large language models (LLMs) on accounting practices and explores future application scenarios. Through a systematic literature review, it highlights the potential of LLMs to enhance efficiency, transparency and innovation across areas such as financial reporting, ESG disclosure, financial analysis and risk management. Additionally, it identifies key challenges, including data quality, privacy and the need for domain-specific adaptations, while proposing actionable strategies to address them. By forecasting advanced applications like intelligent knowledge bases and automated operations, this study provides a roadmap for integrating LLMs into accounting, driving progress and sustainability in the industry.Design/methodology/approach: This study adopts a systematic literature review methodology to explore the impact and future applications of LLMs in accounting. It identifies key research areas by analyzing over 50 high-quality studies selected through extensive keyword searches, Boolean queries and backward and forward citation analyses of seminal works. The review is structured around eight thematic areas, including financial reporting, ESG disclosure and risk management. By synthesizing findings, the study develops a comprehensive framework for understanding the transformative potential of LLMs while addressing associated challenges, such as data security and specialization, to guide future research and practical applications in accounting.Findings: The study reveals that LLMs significantly enhance efficiency, transparency and innovation in accounting by automating processes like financial reporting, ESG disclosure and risk management. They enable advanced applications such as intelligent knowledge bases, budget optimization and automated contract management. However, challenges remain, including the need for high-quality data, domain-specific model training, interdisciplinary talent development and robust data security measures. The findings underscore LLMs’ potential to transform accounting practices while emphasizing the importance of theoretical frameworks and strategic planning to address these challenges and fully realize their benefits in driving industry progress and sustainability.Practical implications: The study highlights practical pathways for integrating LLMs into accounting, emphasizing their potential to automate processes, enhance decision-making and improve operational efficiency. Organizations can leverage LLMs for tasks such as financial reporting, ESG analysis and risk management, reducing manual effort and increasing accuracy. Practical implications include the need for targeted training of LLMs in accounting-specific contexts, robust data governance to ensure quality and security and developing interdisciplinary skills among accounting professionals. By addressing these areas, organizations can harness LLMs to drive innovation, streamline operations and achieve sustainable growth in a rapidly evolving business environment.Originality/value: This study provides a comprehensive and systematic analysis of the transformative impact of LLMs on accounting, addressing gaps in fragmented research and limited practical insights. It uniquely integrates theoretical perspectives with practical applications, offering a structured framework for understanding LLMs’ role across multiple accounting domains. By identifying key challenges and proposing actionable strategies, the paper delivers original value to both researchers and practitioners, fostering innovation and guiding the integration of LLMs into accounting practices. Its forward-looking approach offers a valuable resource for advancing knowledge and shaping the future of accounting in the digital age.
- 9 May 2025
- Published by Emerald Publishing in Journal of Accounting Literature
- Vol. ahead-of-p (ahead-of-p)
The impact of large language models on accounting and future application scenarios
Purpose: This paper examines the transformative impact of large language models (LLMs) on accounting practices and explores future application scenarios. Through a systematic literature review, it highlights the potential of LLMs to enhance efficiency, transparency and innovation across areas such as financial reporting, ESG disclosure, financial analysis and risk management. Additionally, it identifies key challenges, including data quality, privacy and the need for domain-specific adaptations, while proposing actionable strategies to address them. By forecasting advanced applications like intelligent knowledge bases and automated operations, this study provides a roadmap for integrating LLMs into accounting, driving progress and sustainability in the industry.Design/methodology/approach: This study adopts a systematic literature review methodology to explore the impact and future applications of LLMs in accounting. It identifies key research areas by analyzing over 50 high-quality studies selected through extensive keyword searches, Boolean queries and backward and forward citation analyses of seminal works. The review is structured around eight thematic areas, including financial reporting, ESG disclosure and risk management. By synthesizing findings, the study develops a comprehensive framework for understanding the transformative potential of LLMs while addressing associated challenges, such as data security and specialization, to guide future research and practical applications in accounting.Findings: The study reveals that LLMs significantly enhance efficiency, transparency and innovation in accounting by automating processes like financial reporting, ESG disclosure and risk management. They enable advanced applications such as intelligent knowledge bases, budget optimization and automated contract management. However, challenges remain, including the need for high-quality data, domain-specific model training, interdisciplinary talent development and robust data security measures. The findings underscore LLMs’ potential to transform accounting practices while emphasizing the importance of theoretical frameworks and strategic planning to address these challenges and fully realize their benefits in driving industry progress and sustainability.Practical implications: The study highlights practical pathways for integrating LLMs into accounting, emphasizing their potential to automate processes, enhance decision-making and improve operational efficiency. Organizations can leverage LLMs for tasks such as financial reporting, ESG analysis and risk management, reducing manual effort and increasing accuracy. Practical implications include the need for targeted training of LLMs in accounting-specific contexts, robust data governance to ensure quality and security and developing interdisciplinary skills among accounting professionals. By addressing these areas, organizations can harness LLMs to drive innovation, streamline operations and achieve sustainable growth in a rapidly evolving business environment.Originality/value: This study provides a comprehensive and systematic analysis of the transformative impact of LLMs on accounting, addressing gaps in fragmented research and limited practical insights. It uniquely integrates theoretical perspectives with practical applications, offering a structured framework for understanding LLMs’ role across multiple accounting domains. By identifying key challenges and proposing actionable strategies, the paper delivers original value to both researchers and practitioners, fostering innovation and guiding the integration of LLMs into accounting practices. Its forward-looking approach offers a valuable resource for advancing knowledge and shaping the future of accounting in the digital age.