[图书][B] Statistical foundations of actuarial learning and its applications
MV Wüthrich, M Merz - 2023 - library.oapen.org
This open access book discusses the statistical modeling of insurance problems, a process
which comprises data collection, data analysis and statistical model building to forecast …
which comprises data collection, data analysis and statistical model building to forecast …
LocalGLMnet: interpretable deep learning for tabular data
R Richman, MV Wüthrich - Scandinavian Actuarial Journal, 2023 - Taylor & Francis
Deep learning models have gained great popularity in statistical modeling because they
lead to very competitive regression models, often outperforming classical statistical models …
lead to very competitive regression models, often outperforming classical statistical models …
Non-life insurance risk classification using categorical embedding
P Shi, K Shi - North American Actuarial Journal, 2023 - Taylor & Francis
This article presents several actuarial applications of categorical embedding in the context of
non-life insurance risk classification. In non-life insurance, many rating factors are naturally …
non-life insurance risk classification. In non-life insurance, many rating factors are naturally …
Machine learning with high-cardinality categorical features in actuarial applications
High-cardinality categorical features are pervasive in actuarial data (eg, occupation in
commercial property insurance). Standard categorical encoding methods like one-hot …
commercial property insurance). Standard categorical encoding methods like one-hot …
The use of autoencoders for training neural networks with mixed categorical and numerical features
We focus on modelling categorical features and improving predictive power of neural
networks with mixed categorical and numerical features in supervised learning tasks. The …
networks with mixed categorical and numerical features in supervised learning tasks. The …
Enhancing actuarial non-life pricing models via transformers
A Brauer - European Actuarial Journal, 2024 - Springer
Currently, there is a lot of research in the field of neural networks for non-life insurance
pricing. The usual goal is to improve the predictive power of actuarial pricing and behavioral …
pricing. The usual goal is to improve the predictive power of actuarial pricing and behavioral …
Multiple Yield Curve Modeling and Forecasting using Deep Learning
R Richman, S Scognamiglio - arXiv preprint arXiv:2401.16985, 2024 - arxiv.org
This manuscript introduces deep learning models that simultaneously describe the
dynamics of several yield curves. We aim to learn the dependence structure among the …
dynamics of several yield curves. We aim to learn the dependence structure among the …
The Credibility Transformer
R Richman, S Scognamiglio, MV Wüthrich - arXiv preprint arXiv …, 2024 - arxiv.org
Inspired by the large success of Transformers in Large Language Models, these
architectures are increasingly applied to tabular data. This is achieved by embedding …
architectures are increasingly applied to tabular data. This is achieved by embedding …
Federated learning-based edge computing for automatic train operation in communication-based train control systems
Z Zhang, H Jiang, H Zhao, Y Li - The Journal of Supercomputing, 2024 - Springer
Automatic train operation (ATO) is a critical component of automatic train control (ATC)
systems. The ATO automatically adjusts the speed of trains, ensuring the safety of trains and …
systems. The ATO automatically adjusts the speed of trains, ensuring the safety of trains and …
Reducing the dimensionality and granularity in hierarchical categorical variables
P Wilsens, K Antonio, G Claeskens - arXiv preprint arXiv:2403.03613, 2024 - arxiv.org
Hierarchical categorical variables often exhibit many levels (high granularity) and many
classes within each level (high dimensionality). This may cause overfitting and estimation …
classes within each level (high dimensionality). This may cause overfitting and estimation …