Multiples inputs neural nets for Medicare fraud detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2021

Multiples inputs neural nets for Medicare fraud detection

Réseaux de neurones à entrées multiples pour la détection de fraude en assurances maladie


Medicare fraud results in considerable losses for governments and insurance companies and results in higher premiums from clients. Medicare fraud costs around 13 billion euros in Europe and between 21 billion and 71 billion US dollars per year in the United States. This study aims to use artificial neural network based classifiers to predict medicare fraud. The main difficulty using machine learning techniques in fraud detection or more generally anomaly detection is that the data sets are highly imbalanced. To detect medicare frauds, we use multiple inputs deep neural network based classifier with an autoencoder component. This architecture makes it possible to take into account many sources of data without mixing them and makes the classification task easier for the final model. The latent features extracted from the autoencoder have a strong discriminating power and separate the providers into homogeneous clusters. We use the data sets from the Centers for Medicaid and Medicare Services (CMS) of the US federal government. The CMS provides publicly available data that brings together all of the cost price requests sent by American hospitals to medicare companies. Our results show that although baseline artificial neural network give good performances, they are outperformed by our multiple inputs neural networks. We have shown that using an autoencoder to embed the provider level features gives better results and makes the classifiers more robust to class imbalance.
SofiaSummit2021 (1).pdf (112.7 Ko) Télécharger le fichier
Format Short paper
Origin Files produced by the author(s)

Dates and versions

hal-03500411 , version 1 (22-12-2021)


  • HAL Id : hal-03500411 , version 1


Mansour Zoubeirou a Mayaki, Michel Riveill. Multiples inputs neural nets for Medicare fraud detection. 2021. ⟨hal-03500411⟩
71 View
63 Download


Gmail Mastodon Facebook X LinkedIn More