An empirical comparison finds autoencoder ensembles detect all injected anomalies in two health insurance datasets, outperforming classical unsupervised methods, but the evaluation contains significant tuning and reproducibility gaps.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.AP 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Machine Learning-based Anomaly Detection Framework in Life Insurance Contracts
An empirical comparison finds autoencoder ensembles detect all injected anomalies in two health insurance datasets, outperforming classical unsupervised methods, but the evaluation contains significant tuning and reproducibility gaps.