Blurring the boundaries.
In: Actuary, 2024-04-01, S. 38-40
serialPeriodical
Zugriff:
This article explores different modeling techniques used in predicting loss costs in insurance. The traditional approach of using generalized linear models (GLMs) is still relevant, but new risk factors brought about by automation and new technologies add complexity to their construction. Machine learning models, such as gradient boosting models (GBMs) and artificial neural networks (ANNs), have also proven useful in capturing intricate relationships between risk factors and loss costs. The article compares the predictive accuracy of GLMs, GBMs, ANNs, and a hybrid model that combines a GLM with an ANN. The hybrid model performed the best, followed by the ANN, GBM, and GLM. The study highlights the importance of exploring and comparing advanced modeling approaches to stay ahead of the curve in the insurance industry. [Extracted from the article]
Copyright of Actuary is the property of Redactive Publishing Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Titel: |
Blurring the boundaries.
|
---|---|
Autor/in / Beteiligte Person: | Dhyani, Alisha ; Wilson, Alinta ; Nehme, Antonio |
Zeitschrift: | Actuary, 2024-04-01, S. 38-40 |
Veröffentlichung: | 2024 |
Medientyp: | serialPeriodical |
ISSN: | 0960-457X (print) |
Schlagwort: |
|
Sonstiges: |
|