%0 Conference Paper %1 BaZuGrScHeKo-ICPE20-Seasonal-Forecast %A Bauer, André %A Züfle, Marwin %A Grohmann, Johannes %A Schmitt, Norbert %A Herbst, Nikolas %A Kounev, Samuel %B Proceedings of the ACM/SPEC International Conference on Performance Engineering %C New York, NY, USA %D 2020 %I Association for Computing Machinery (ACM) %K Online_monitoring_and_forecasting PRISMA Prediction descartes t_short myown %P 48--55 %R 10.1145/3358960.3379123 %T An Automated Forecasting Framework based on Method Recommendation for Seasonal Time Series %U https://doi.org/10.1145/3358960.3379123 %X Due to the fast-paced and changing demands of their users, computing systems require autonomic resource management. To enable proactive and accurate decision-making for changes causing a particular overhead, reliable forecasts are needed. In fact, choosing the best performing forecasting method for a given time series scenario is a crucial task. Taking the "No-Free-Lunch Theorem" into account, there exists no forecasting method that performs best on all types of time series. To this end, we propose an automated approach that (i) extracts characteristics from a given time series, (ii) selects the best-suited machine learning method based on recommendation, and finally, (iii) performs the forecast. Our approach offers the benefit of not relying on a single method with its possibly inaccurate forecasts. In an extensive evaluation, our approach achieves the best forecasting accuracy. %@ 9781450369916

@inproceedings{BaZuGrScHeKo-ICPE20-Seasonal-Forecast, abstract = {Due to the fast-paced and changing demands of their users, computing systems require autonomic resource management. To enable proactive and accurate decision-making for changes causing a particular overhead, reliable forecasts are needed. In fact, choosing the best performing forecasting method for a given time series scenario is a crucial task. Taking the "No-Free-Lunch Theorem" into account, there exists no forecasting method that performs best on all types of time series. To this end, we propose an automated approach that (i) extracts characteristics from a given time series, (ii) selects the best-suited machine learning method based on recommendation, and finally, (iii) performs the forecast. Our approach offers the benefit of not relying on a single method with its possibly inaccurate forecasts. In an extensive evaluation, our approach achieves the best forecasting accuracy.}, added-at = {2020-04-06T11:25:46.000+0200}, address = {New York, NY, USA}, author = {Bauer, Andr{\'e} and Z{\"u}fle, Marwin and Grohmann, Johannes and Schmitt, Norbert and Herbst, Nikolas and Kounev, Samuel}, biburl = {https://www.bibsonomy.org/bibtex/2c6d9b255658bcdb54fa60265e7ac46b7/marwin.zuefle}, booktitle = {Proceedings of the ACM/SPEC International Conference on Performance Engineering}, doi = {10.1145/3358960.3379123}, interhash = {1f425c77f470c6d01ab0545f8d8efa00}, intrahash = {c6d9b255658bcdb54fa60265e7ac46b7}, isbn = {9781450369916}, keywords = {Online_monitoring_and_forecasting PRISMA Prediction descartes t_short myown}, month = {April}, pages = {48--55}, publisher = {Association for Computing Machinery (ACM)}, series = {ICPE '20}, timestamp = {2022-11-16T09:11:03.000+0100}, title = {{An Automated Forecasting Framework based on Method Recommendation for Seasonal Time Series}}, url = {https://doi.org/10.1145/3358960.3379123}, venue = {Edmonton AB, Canada}, year = 2020 }