BERT4LossPrediction Software Package

The following package

  • software tool source code in Python
    was developed based on the project supported by the Casualty Actuarial Society (CAS) on Framework of BERT-Based NLP Models for Frequency and Severity in Insurance Claims, a paper to be published in Variance, the Casualty Actuarial Society Research Journal:
  • Shuzhe Xu, Vajira Manathunga, and Don Hong, Framework of BERT-Based NLP Models for Frequency and Severity in Insurance Claims, Variance, to appear.

    The following relative paper published in the journal of Insurance: Mathematics and Economics recently is for your reference if you are interested in using BERT-based NLP Techniques for actuarial modeling:

  • Shuzhe Xu, Chuanlong Zhang, Don Hong, BERT BASED NLP TECHNIQUES FOR CLASSIFICATION AND SEVERITY MODELING IN BASIC WARRANTY DATA STUDY, Insurance: Mathematics and Economics, Volume 107 (2022), 57-67. DOI.

    Please send your comment to Don Hong or Shuzhe Xu.

    Back to Don Hong's Home Page