Unsupervised Anomaly Detection for Discrete Sequence Healthcare Data

Fraud in healthcare is widespread, as doctors could prescribe unnecessary treatments to increase bills. Insurance companies want detect these anomalous fraudulent bills and reduce their losses. Traditional fraud detection methods use expert rules manual data processing. Recently, machine learning techniques automate this process, but hand-labeled extremely costly usually out of date. We propose a model that automates an unsupervised way. Two deep approaches include LSTM neural network for prediction next patient visit seq2seq model. For normalization produced anomaly scores, we Empirical Distribution Function (EDF) approach. So, the algorithm works with high class imbalance problems.