In particular, a common task when observing a signal is that of anomaly detection, i.e. the detection of deviations from a certain normal mode of operation. We are provided with high frequency time series data. The goal of this project is to apply an algorithm (or several of them) to detect anomalies if there are any.

Deliverables: 

• Analysis of provided data (visualization, statistics, etc., basically what you think should be there)

• Formulation of the solution method(s) and its implementation

• Interpretation and visualization of results

I used simple statistical techniques and machine learning algorithms (Isolation Forest and LSTM Autoencoder) to detect anomalies.