Skip to main content

Actuarial Data Science

  • 445 Accesses


Insurance companies have always been dependent on reliable projections and hence on data-driven decisions. As digitalization is progressing in almost every industry, insurance companies may benefit in particular, because they already possess valuable historical data. Not only is process automation, for example in the settlement of claims or the distribution of insurance contracts, worth considering, but the traditional fields of work of actuaries, for example, pricing, reserving, or investment, also offer various applications for machine learning algorithms. This chapter gives an overview of actuarial data science with promising use cases where existing models can be enhanced or even replaced and presents the important prerequisites that need to be taken into account.


  • Data Science
  • Actuarial Science
  • Actuary
  • Actuarial Models
  • Fraud
  • Lapse
  • Pricing
  • Reserving
  • Risk Management
  • Solvency II

This is a preview of subscription content, access via your institution.

Buying options

USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-78814-8_8
  • Chapter length: 18 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
USD   69.99
Price excludes VAT (USA)
  • ISBN: 978-3-030-78814-8
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Hardcover Book
USD   89.99
Price excludes VAT (USA)


  1. 1.

    Machine learning techniques for investment or asset portfolio management are not addressed in this chapter as this has a much wider range of application and is not restricted to actuarial practice.

  2. 2.

    An interesting combination of RPA and machine learning can be found in (RPA—Use Case SPPI see [Gabriel 2021]).

  3. 3.

  4. 4.

    Property and casualty insurance.

  5. 5.

    In GLMs the response variable comes from an exponential family distribution, for example Normal, Exponential, Binomial or Poisson distribution.

  6. 6.

    The ML approaches applied were Extreme Gradient Boosting and Support Vector Machines.

  7. 7.

    Adverse selection is defined as the information asymmetry between the policyholder and the insurance company.

  8. 8.

    See, for example, Society of Actuaries (SOA): or the Social Security Administration (SSA):

  9. 9.

    For example, EIOPA has established an Expert Group on Digital Ethics in Insurance:

  10. 10.

    For example, the European Actuary Association (EEA) recently hosted the Data Science & Data Ethics e-Conference in June 2020:

  11. 11.


Download references

Author information

Authors and Affiliations


Corresponding author

Correspondence to Susanne Brindöpke .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Verify currency and authenticity via CrossMark

Cite this chapter

Brindöpke, S. (2021). Actuarial Data Science. In: Liermann, V., Stegmann, C. (eds) The Digital Journey of Banking and Insurance, Volume I. Palgrave Macmillan, Cham.

Download citation

  • DOI:

  • Published:

  • Publisher Name: Palgrave Macmillan, Cham

  • Print ISBN: 978-3-030-78813-1

  • Online ISBN: 978-3-030-78814-8

  • eBook Packages: Economics and FinanceEconomics and Finance (R0)