Master’s student or intern Anomaly Detection with Explainability & Causality on High-dimensional Time Series

Job Description

Project

We shall address the problem of detecting, predicting and explaining general anomalies in high-dimension KPI performance metrics, i.e., high cardinal and large dynamic range multivariate non-stationary time series collected from real Cloud IT environments. Using Keras/TF etc., we will build an ML-based AD framework for transfer, attention and meta-learning that must remain robust also with reduced/missing and noisy training data. Besides feature engineering — e.g., selection, reduction, compression techniques — Explainability and Causality will also be necessary for the ML model prototype.

Requirements

• Data science/mining in general, multivariate timeseries in particular, also including logs and tickets (NLP mappings, embeddings);
• Feature engineering and DL experience with RNN/CNN/TCN-based xAutoencoders in particular;
• Hands-on experience with deep neural network models in Python, NumPy, Pandas, SciPy etc. applied to deep RNN/CNN/Autoencoders, ideally also including Explainability and Causality methods;
• Motivation to learn real-life time series and experiment with DL in Keras/TensorFlow/PyTorch etc.