@inproceedings{Trifunov21_ICMLA,
    type = {inproceedings},
    key = {Trifunov21_ICMLA},
    title = {Anomaly Attribution of Multivariate Time Series using Counterfactual Reasoning},
    author = {Violeta Teodora Trifunov and Maha Shadaydeh and Björn Barz and Joachim Denzler},
    booktitle = {IEEE International Conference on Machine Learning and Applications (ICMLA)},
    year = {2021},
    pages = {166-172},
    abstract = {There are numerous methods for detecting anomalies in time series, but that is only the first step to understanding them. We strive to exceed this by explaining those anomalies. Thus we develop a novel attribution scheme for multivariate time series relying on counterfactual reasoning. We aim to answer the counterfactual question of would the anomalous event have occurred if the subset of the involved variables had been more similarly distributed to the data outside of the anomalous interval. Specifically, we detect anomalous intervals using the Maximally Divergent Interval (MDI) algorithm, replace a subset of variables with their in-distribution values within the detected interval and observe if the interval has become less anomalous, by re-scoring it with MDI. We evaluate our method on multivariate temporal and spatio-temporal data and confirm the accuracy of our anomaly attribution of multiple well-understood extreme climate events such as heatwaves and hurricanes.},
    doi = {10.1109/ICMLA52953.2021.00033},
    groups = {noveltydetection,anomaly detection},
    url = {https://ieeexplore.ieee.org/document/9680191},
}