Convolutional Neural Network Case Studies: (1) Anomalies in Mortality Rates (2) Image Recognition

24 Pages Posted: 8 Oct 2020

See all articles by Daniel Meier

Daniel Meier

Swiss Reinsurance Company

Mario V. Wuthrich

RiskLab, ETH Zurich

Date Written: July 19, 2020

Abstract

We provide a general introduction to convolutional neural networks (CNNs) in this tutorial. CNNs are particularly well suited to find common spatial structure in images or time series. As an insurance related example for life & health insurance we illustrate how to use a CNN to detect anomalies in mortality rates taken from the Human Mortality Database (HMD); the anomalies are caused by migration between countries and other errors. As a second example, we study a CNN to classify images of handwritten digits taken from one of the most widely used benchmark datasets, the Modified National Institute of Standards and Technology (MNIST) dataset. Our aim is to explore and discuss the building blocks and the properties of these CNNs, and we showcase their use.

Keywords: convolutional neural network, CNN, regression, classification, mortality rates

JEL Classification: G22

Suggested Citation

Meier, Daniel and Wuthrich, Mario V., Convolutional Neural Network Case Studies: (1) Anomalies in Mortality Rates (2) Image Recognition (July 19, 2020). Available at SSRN: https://ssrn.com/abstract=3656210 or http://dx.doi.org/10.2139/ssrn.3656210

Daniel Meier (Contact Author)

Swiss Reinsurance Company ( email )

Mythenquai 50/60
P.O. Box
CH-8022 Zurich
Switzerland

Mario V. Wuthrich

RiskLab, ETH Zurich ( email )

Department of Mathematics
Ramistrasse 101
Zurich, 8092
Switzerland

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
821
Abstract Views
2,417
Rank
52,217
PlumX Metrics