Featured Product

    Janet Zhao

    Leads RiskCalc™ model development and R&D of new products, actively advises clients on best practices in credit risk management, and provides thought leadership

    Janet Zhao oversees RiskCalc model development and related customer support. She also spearheads R&D behind new product development. She has served as a senior advisor to complex consulting projects. Janet’s expertise includes credit risk management, stress testing, and financial reporting. She has spoken frequently at conferences and seminars, and published in academic and practitioner journals.

    City University of Hong Kong: PhD, Finance
    Carnegie Mellon University: PhD, Accounting

    Credit Risk Modeling: Moody’s Analytics delivers award-winning credit models and expert advisory services to provide you with best-in-class credit risk modeling solutions.

    Financial Data: Moody's Analytics financial data solutions enable you to assess market opportunities and compare entities across systems.

    Stress Testing: Moody’s Analytics helps financial institutions develop collaborative, auditable, repeatable, and transparent stress testing programs to meet regulatory demands.

    Allowance for Loan and Lease Losses (ALLL): Calculate fast, accurate reserves for loan and lease losses with our cloud-based ALLL solution.


    Enterprise Risk: Business strategy to identify, assess, and prepare for any dangers to a firm's operations.

    Financial Reporting and Accounting: Accounting field concerned with financial transaction summary, analysis, and reporting.

    Representative Projects

    VeritasScore, a highly effective financial misconduct detection tool. This tool assigns a quality score to a set of financial statements, with a detailed report supporting the score. Statements with a high score provide relevant and reliable representation of the firm’s financial conditions. Low-quality statements may come from mistakes, aggressive accounting practices, or fraud.

    Machine learning in credit decisioning, an article cited by Financial Times and the CFA level II textbook. Using two large datasets, we analyze the performance of a set of machine learning methods in assessing credit risk of small and medium-sized borrowers. Machine learning methods provide a better fit for the nonlinear relationships between the explanatory variables and default risk than existing methods.

    Published Work