Corpus ID: 208637000

Generative Synthesis of Insurance Datasets

  title={Generative Synthesis of Insurance Datasets},
  author={K. Kuo},
  • K. Kuo
  • Published 2019
  • Computer Science, Mathematics, Economics
  • ArXiv
  • One of the impediments in advancing actuarial research and developing open source assets for insurance analytics is the lack of realistic publicly available datasets. In this work, we develop a workflow for synthesizing insurance datasets leveraging CTGAN, a recently proposed neural network architecture for generating tabular data. Applying the proposed workflow to publicly available data in the domains of general insurance pricing and life insurance shock lapse modeling, we evaluate the… CONTINUE READING
    1 Citations

    Figures and Tables from this paper.

    Machine Learning for Financial Risk Management: A Survey


    Data Analytics for Non-Life Insurance Pricing
    • 32
    Modeling Tabular data using Conditional GAN
    • 33
    • Highly Influential
    • PDF
    Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
    • 193
    • PDF
    An Individual Claims History Simulation Machine
    • 14
    • PDF
    PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees
    • 65
    AI in Actuarial Science
    • 10
    Differentially Private Generative Adversarial Network
    • 94
    • PDF
    LOGAN: Membership Inference Attacks Against Generative Models
    • 108
    • PDF
    PacGAN: The Power of Two Samples in Generative Adversarial Networks
    • 116
    • PDF