Ajay Chawda, Stefanie Grimm, Marius Kloft
In this paper, we introduce the Vehicle Claims dataset, consisting of fraudulent insurance claims for automotive repairs. The data belongs to the more broad category of Auditing data, which includes also Journals and Network Intrusion data. Insurance claim data are distinctively different from other auditing data (such as network intrusion data) in their high number of categorical attributes. We tackle the common problem of missing benchmark datasets for anomaly detection: datasets are mostly confidential, and the public tabular datasets do not contain relevant and sufficient categorical attributes. Therefore, a large-sized dataset is created for this purpose and referred to as Vehicle Claims (VC) dataset. The dataset is evaluated on shallow and deep learning methods. Due to the introduction of categorical attributes, we encounter the challenge of encoding them for the large dataset. As One Hot encoding of high cardinal dataset invokes the "curse of dimensionality", we experiment with GEL encoding and embedding layer for representing categorical attributes. Our work compares competitive learning, reconstruction-error, density estimation and contrastive learning approaches for Label, One Hot, GEL encoding and embedding layer to handle categorical values.
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Anomaly Detection | Vehicle Claims | AUC | 98.65 | Random Forest |
| Anomaly Detection | Vehicle Claims | AUC | 95.88 | Gradient Boosting |
| Anomaly Detection | Vehicle Claims | AUC | 65.43 | SOM |
| Anomaly Detection | Vehicle Claims | AUC | 59.42 | Isolation Forest |
| Anomaly Detection | Vehicle Claims | AUC | 58.59 | Latent Outlier Exposure |
| Anomaly Detection | Vehicle Claims | AUC | 57.03 | NeuTraL-AD |
| Anomaly Detection | Vehicle Claims | AUC | 55.38 | RSRAE |
| Anomaly Detection | Vehicle Claims | AUC | 53.82 | SOM-DAGMM |
| Anomaly Detection | Vehicle Claims | AUC | 52.86 | Local Outlier Factor |
| Anomaly Detection | Vehicle Claims | AUC | 51.68 | One Class Support Vector Machines |
| Anomaly Detection | Vehicle Claims | AUC | 51.22 | DAGMM |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 65.43 | SOM |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 59.42 | Isolation Forest |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 58.59 | Latent Outlier Exposure |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 57.03 | NeuTraL-AD |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 55.38 | RSRAE |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 53.82 | SOM-DAGMM |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 52.86 | Local Outlier Factor |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 51.68 | One Class Support Vector Machines |
| Unsupervised Anomaly Detection | Vehicle Claims | AUC | 51.22 | DAGMM |