JHJing He

Jing He

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jing He has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Privacy-Preserving Credit Risk Prediction with Alternative Data

    by Hongzhe Zhang, Jiarong Xu, Jing He, Xiao Fang

    Credit risk prediction, or how to develop predictive models that aid financial institutions in granting and managing consumer credit, is a critical problem in the consumer credit industry. Traditionally, financial institutions construct credit risk prediction models using borrowers' demographic, financial, and credit history data, collectively referred to as traditional data. Recent studies have demonstrated that alternative data, such as borrowers' mobile phone communication data, enable lenders to acquire fuller and more accurate profiles of borrowers' creditworthiness, thereby improving credit risk prediction performance. Nevertheless, alternative data are held by external entities independent of financial institutions. Directly sharing alternative data with financial institutions infringes on consumer privacy, yet existing credit risk prediction studies largely overlook this issue. To address this research gap, we define a new problem, namely privacy-preserving credit risk prediction with alternative data, which simultaneously considers three practical constraints for building credit risk prediction models with alternative data: the privacy-preserving constraint that protects consumer privacy, the model-confidentiality constraint that learns and stores the model centrally at the financial institution, and the lossless constraint that maintains the performance of the learned model. To solve this problem, we develop PrivacyCredit, a novel privacy-preserving machine learning method. We then theoretically demonstrate the privacy-preserving, model-confidential, and lossless properties of Priva-cyCredit. Through extensive experiments using a real-world credit dataset linked with alternative data, we demonstrate the predictive value of securely incorporating alternative data into credit risk prediction and show that PrivacyCredit achieves the same predictive performance as the model learned from the insecure plaintext combination of traditional and alternative data. We further evaluate its model-confidentiality property and computational efficiency, showing that PrivacyCredit can be practically implemented for credit risk prediction.

  • Open Access

    Do Chief Accounting Officers Influence Corporate Disclosure?

    by He Jennifer Wen, Jing He, Marlene A. Plumlee

    This study explores aspects of chief accounting officers (CAOs), a relatively new corporate executive title that firms add to C-suites. We provide descriptive data on CAO attributes and examine the determinants of CAO appointment and their role in corporate disclosure. Our results suggest that firms’ decisions to appoint a CAO are positively associated with investor sophistication and reporting environment. We find that CAO presence is positively associated with the quality of firms’ voluntary and mandatory disclosures, as measured by the amount of information disclosed in 8-K filings. Further investigation of voluntary disclosures via specific channels reveals that the presence of a CAO is positively associated with both the frequency of management guidance and non-GAAP disclosures. We also find that firms with CAOs take more time to issue earnings announcements, especially for larger firms. Additional analysis indicates that having a CAO in the executive team is not merely a title change. Instead, CAOs bring expertise and monitoring to corporate disclosure.

  • Open Access

    Exploiting Expert Knowledge for Assigning Firms to Industries: A Novel Deep Learning Method

    by Xiaohang Zhao, Xiao Fang, Jing He, Lihua Huang

    Industry assignment, which assigns firms to industries according to a predefined Industry Classification System (ICS), is fundamental to a large number of critical business practices, ranging from operations and strategic decision making by firms to economic analyses by government agencies. Three types of expert knowledge are essential to effective industry assignment: definition-based knowledge (i.e., expert definitions of each industry), structure-based knowledge (i.e., structural relationships among industries as specified in an ICS), and assignment-based knowledge (i.e., prior firm-industry assignments performed by domain experts). Existing industry assignment methods utilize only assignment-based knowledge to learn a model that classifies unassigned firms to industries, and overlook definition-based and structure-based knowledge. Moreover, these methods only consider which industry a firm has been assigned to, but ignore the time-specificity of assignment-based knowledge, i.e., when the assignment occurs. To address the limitations of existing methods, we propose a novel deep learning-based method that not only seamlessly integrates the three types of knowledge for industry assignment but also takes the time-specificity of assignment-based knowledge into account. Methodologically, our method features two innovations: dynamic industry representation and hierarchical assignment. The former represents an industry as a sequence of time-specific vectors by integrating the three types of knowledge through our proposed temporal and spatial aggregation mechanisms. The latter takes industry and firm representations as inputs, computes the probability of assigning a firm to different industries, and assigns the firm to the industry with the highest probability. We conduct extensive evaluations with two widely used ICSs and demonstrate the superiority of our method over prevalent existing methods.


  • Executive Network Centrality and Corporate Reporting

    by Jing He

    This paper investigates the association of corporate reporting and executive network centrality, which measures an executive’s relative position in a massive network consisting of outside corporate leaders. I find that high-centrality chief executive officers (CEOs) and chief financial officers (CFOs) are generally more likely to engage in financial misreporting than low-centrality CEOs and CFOs. I also find that the influence of CFO network centrality is greater than that of CEOs in financial misreporting. Further analyses show that the monitoring effect of internal governance mechanisms on high-centrality executives is very limited and that the discipline of the managerial labor market is weaker for high-centrality CFOs as well. My results hold for a subsample subject to exogenous shocks to CFO connectedness and are robust to a series of alternative specifications including using CFO fixed effects. Taken together, my findings suggest that corporate reporting can be influenced by executives’ social network position, with high-centrality CFOs using their social power to make adverse corporate reporting decisions to gain personal benefits. This paper was accepted by Brian Bushee, accounting.


  • Measuring disclosure using 8-K filings

    by Jing He, Marlene A. Plumlee