EconBase
← All papers

A Self-Attention Network for Hierarchical Data Structures with an Application to Claims Management

Leander Löw, Martin Spindler, Eike Brechmann

arXiv 30 Aug 2018 · Machine Learning

arXiv:1808.10543 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Insurance companies must manage millions of claims per year. While most of these claims are non-fraudulent, fraud detection is core for insurance companies. The ultimate goal is a predictive model to single out the fraudulent claims and pay out the non-fraudulent ones immediately. Modern machine learning methods are well suited for this kind of problem. Health care claims often have a data structure that is hierarchical and of variable length. We propose one model based on piecewise feed forward neural networks (deep learning) and another model based on self-attention neural networks for the task of claim management. We show that the proposed methods outperform bag-of-words based models, hand designed features, and models based on convolutional neural networks, on a data set of two million health care claims. The proposed self-attention method performs the best.

Citation extraction

9
references
10
in-text mentions
9
distinct cited
0
self-citations
4,487
main-text words

appendix boundary found by none_found · 100% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Vaswani, Ashish, Shazeer, Noam, Parmar, Niki, Uszkoreit, Jakob, Jone… Attention Is All You Need0.64422100%
2Ba, Jimmy Lei, Kiros, Jamie Ryan, and Hinton, Geoffrey E Layer Normalization0.40511100%
3Bahdanau, Dzmitry, Cho, Kyunghyun, and Bengio, Yoshua (2014) Neural Machine Translation by Jointly Learning to Align and Translate0.40511100%
4Graves, Alex (2012) Supervised Sequence Labelling0.40511100%
5Guo, Cheng and Berkhahn, Felix Entity Embeddings of Categorical Variables0.40511100%
6Kim, Yoon (2014) Convolutional Neural Networks for Sentence Classification0.40511100%
7Mikolov, Tomas, Chen, Kai, Corrado, Greg, and Dean, Jeffrey (2013) Efficient Estimation of Word Representations in Vector Space0.40511100%
8Shen, Tao, Zhou, Tianyi, Long, Guodong, Jiang, Jing, Pan, Shirui, an… DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding0.40511100%
9Wu, Songtao, Zhong, Shenghua, and Liu, Yan (2017) Deep residual learning for image steganalysis0.40511100%

Showing the top 9 of 9 scored citations.