The use of autoencoders for training neural networks with mixed categorical and numerical features

DOI10.1017/ASB.2023.15zbMATH Open1520.91322OpenAlexW4366823716MaRDI QIDQ6174075FDOQ6174075

Authors: Łukasz Delong 

Publication date: 13 July 2023

Published in: ASTIN Bulletin (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1017/asb.2023.15

Recommendations

• A hybrid neural network for input that is both categorical and quantitative
• Model-aware categorical data embedding: a data-driven approach
• Neural network embedding of the over-dispersed Poisson reserving model
• A semi-supervised regression model for mixed numerical and categorical variables
• Gamma mixture density networks and their application to modelling insurance claim amounts

zbMATH Keywords

embeddingsrepresentation learningautoencoderscategorical and numerical featuresinitialization of neural networks

Mathematics Subject Classification ID

Actuarial mathematics (91G05) Artificial neural networks and deep learning (68T07)

Cites Work

• Multiple factor analysis by example using R
• Why does unsupervised pre-training help deep learning?
• Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion
• Machine learning in finance. From theory to practice
• A neural-network analyzer for mortality forecast
• Feature extraction from telematics car driving heatmaps
• Actuarial applications of word embedding models
• A hybrid neural network for input that is both categorical and quantitative
• Extending the Lee-Carter model with variational autoencoder: A fusion of neural network and Bayesian approach
• Geographic ratemaking with spatial embeddings

Cited In (6)

• Machine learning with high-cardinality categorical features in actuarial applications
• A hybrid neural network for input that is both categorical and quantitative
• Model-aware categorical data embedding: a data-driven approach
• Enhancing actuarial non-life pricing models via transformers
• High-cardinality categorical covariates in network regressions
• Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features

This page was built for publication: The use of autoencoders for training neural networks with mixed categorical and numerical features

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6174075)