Insights from Inside Neural Networks
METADATA ONLY
Loading...
Author / Producer
Date
2018-08-19
Publication Type
Working Paper
ETH Bibliography
yes
Citations
Web of Science:
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
We provide a tutorial that illuminates the aspects which need to be considered when fitting neural network regression models to claims frequency data in insurance. We discuss feature pre-processing, choice of loss function, choice of neural network architecture, class imbalance problem, as well as over-fitting. This discussion is based on a publicly available real car insurance data set.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
Pages / Article No.
Publisher
Elsevier
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Neural Networks; Architecture; Over-Fitting; Loss Function; Dropout; Regularization; LASSO; Ridge; Gradient Descent; Class Imbalance; Car Insurance; Claims Frequency; Poisson Regression Model; Machine Learning; Deep Learning
Organisational unit
08813 - Wüthrich, Mario Valentin (Tit.-Prof.)