AA-forecast: anomaly-aware forecast for extreme events. (English) Zbl 1521.62178
Summary: Time series models often are impacted by extreme events and anomalies, both prevalent in real-world datasets. Such models require careful probabilistic forecasts, which is vital in risk management for extreme events such as hurricanes and pandemics. However, it’s challenging to automatically detect and learn from extreme events and anomalies for large-scale datasets which often results in extra manual efforts. Here, we propose an anomaly-aware forecast framework that leverages the effects of anomalies to improve its prediction accuracy during the presence of extreme events. Our model has trained to extract anomalies automatically and incorporates them through an attention mechanism to increase the accuracy of forecasts during extreme events. Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner. The proposed framework demonstrated consistent superior accuracy with less uncertainty on three datasets with different varieties of anomalies over the current prediction models.
MSC:
| 62M20 | Inference from stochastic processes and prediction |
| 62M10 | Time series, auto-correlation, regression, etc. in statistics (GARCH) |
References:
| [1] | Adilova L, Chen S, Kamp M (2021) Novelty detection in sequential data by informed clustering and modeling. arXiv preprint arXiv:2103.03943 |
| [2] | Bartik AW, Bertrand M, Lin F, Rothstein J, Unrath M (2020) Labor market impacts of covid-19 on hourly workers in small-and medium-sized businesses: four facts from homebase data. Institute for Research on Labor and Employment |
| [3] | Box, GE; Pierce, DA, Distribution of residual autocorrelations in autoregressive-integrated moving average time series models, J Am Stat Assoc, 65, 332, 1509-1526 (1970) · Zbl 0224.62041 · doi:10.1080/01621459.1970.10481180 |
| [4] | Broska, LH; Poganietz, WR; Vögele, S., Extreme events defined—a conceptual discussion applying a complex systems approach, Futures, 115 (2020) · doi:10.1016/j.futures.2019.102490 |
| [5] | Cai, L.; Janowicz, K.; Mai, G.; Yan, B.; Zhu, R., Traffic transformer: capturing the continuity and periodicity of time series for traffic forecasting, Trans GIS, 24, 3, 736-755 (2020) · doi:10.1111/tgis.12644 |
| [6] | Cleveland, RB; Cleveland, WS; McRae, JE; Terpenning, I., Stl: a seasonal-trend decomposition, J Off Stat, 6, 1, 3-73 (1990) |
| [7] | Cleveland, WS, Robust locally weighted regression and smoothing scatterplots, J Am Stat Assoc, 74, 368, 829-836 (1979) · Zbl 0423.62029 · doi:10.1080/01621459.1979.10481038 |
| [8] | Dokumentov A, Hyndman RJ (2020) Str: A seasonal-trend decomposition procedure based on regression. arXiv preprint arXiv:2009.05894 |
| [9] | Gal Y, Ghahramani Z (2016) Dropout as a bayesian approximation: representing model uncertainty in deep learning. In: international conference on machine learning, pp. 1050-1059 |
| [10] | Grace D, Christiansen T (2013) Risk-based assessment of unplanned outage events and costs for combined-cycle plants. J Eng Gas Turbines Power 135(2) |
| [11] | Hochreiter, S.; Schmidhuber, J., Long short-term memory, Neural Comput, 9, 8, 1735-1780 (1997) · doi:10.1162/neco.1997.9.8.1735 |
| [12] | Jing, M.; Ng, KY; Mac Namee, B.; Biglarbeigi, P.; Brisk, R.; Bond, R.; Finlay, D.; McLaughlin, J., Covid-19 modelling by time-varying transmission rate associated with mobility trend of driving via apple maps, J Biomedi Inform, 122 (2021) · doi:10.1016/j.jbi.2021.103905 |
| [13] | Khan, A.; Bibi, S.; Lyu, J.; Latif, A.; Lorenzo, A., Covid-19 and sectoral employment trends: assessing resilience in the us leisure and hospitality industry, Curr Issues Tour, 24, 7, 952-969 (2021) · doi:10.1080/13683500.2020.1850653 |
| [14] | Khandelwal U, He H, Qi P, Jurafsky D (2018) Sharp nearby, fuzzy far away: How neural language models use context. arXiv preprint arXiv:1805.04623 |
| [15] | Labach A, Salehinejad H, Valaee S (2019) Survey of dropout methods for deep neural networks. arXiv preprint arXiv:1904.13310 |
| [16] | Laptev N, Yosinski J, Li LE, Smyl S (2017) Time-series extreme event forecasting with neural networks at uber. In: International Conference on Machine Learning, vol. 34, pp. 1-5 |
| [17] | Li L, Yan J, Yang X, Jin Y (2019) Learning interpretable deep state space model for probabilistic time series forecasting. In: IJCAI, pp. 2901-2908 |
| [18] | Li S, Jin X, Xuan Y, Zhou X, Chen W, Wang YX, Yan X (2019) Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting. In: Advances in Neural Information Processing Systems, pp. 5243-5253 |
| [19] | Lim B, Arik SO, Loeff N, Pfister T (2019) Temporal fusion transformers for interpretable multi-horizon time series forecasting. arXiv preprint arXiv:1912.09363 |
| [20] | Oceanic N, Administration A Nhc data archive. https://www.nhc.noaa.gov/data/. (Accessed on 08/20/2022) |
| [21] | Pang, J.; Liu, D.; Peng, Y.; Peng, X., Anomaly detection based on uncertainty fusion for univariate monitoring series, Measurement, 95, 280-292 (2017) · doi:10.1016/j.measurement.2016.10.031 |
| [22] | Rolnick D, Donti PL, Kaack LH, Kochanski K, Lacoste A, Sankaran K, Ross AS, Milojevic-Dupont N, Jaques N, Waldman-Brown A, et al (2019) Tackling climate change with machine learning. arXiv preprint arXiv:1906.05433 |
| [23] | Sagheer, A.; Kotb, M., Unsupervised pre-training of a deep lstm-based stacked autoencoder for multivariate time series forecasting problems, Sci Rep, 9, 1, 1-16 (2019) · doi:10.1038/s41598-019-55320-6 |
| [24] | Salinas, D.; Flunkert, V.; Gasthaus, J.; Januschowski, T., Deepar: probabilistic forecasting with autoregressive recurrent networks, Int J Forecast, 36, 3, 1181-1191 (2020) · doi:10.1016/j.ijforecast.2019.07.001 |
| [25] | Santos-Burgoa, C.; Sandberg, J.; Suárez, E.; Goldman-Hawes, A.; Zeger, S.; Garcia-Meza, A.; Pérez, CM; Estrada-Merly, N.; Colón-Ramos, U.; Nazario, CM, Differential and persistent risk of excess mortality from hurricane maria in puerto rico: a time-series analysis, Lancet Planet Health, 2, 11, e478-e488 (2018) · doi:10.1016/S2542-5196(18)30209-2 |
| [26] | Selerio, E.; Maglasang, R., Minimizing production loss consequent to disasters using a subsidy optimization model: a pandemic case, Struct Chang Econ Dyn, 58, 112-124 (2021) · doi:10.1016/j.strueco.2021.05.002 |
| [27] | Smith AB (2022) 2021 us billion dollar weather and climate disasters in historical context including new county-level exposure, vulnerability and projected damage mapping. In: 102nd American Meteorological Society Annual Meeting. AMS |
| [28] | Tarsitano, A.; Amerise, IL, Short-term load forecasting using a two-stage sarimax model, Energy, 133, 108-114 (2017) · doi:10.1016/j.energy.2017.05.126 |
| [29] | Tolstikhin, IO; Houlsby, N.; Kolesnikov, A.; Beyer, L.; Zhai, X.; Unterthiner, T.; Yung, J.; Steiner, A.; Keysers, D.; Uszkoreit, J., Mlp-mixer: an all-mlp architecture for vision, Adv Neural Inform Process Syst, 34, 24261-24272 (2021) |
| [30] | Wahab, H.; Jain, V.; Tyrrell, AS; Seas, MA; Kotthoff, L.; Johnson, PA, Machine-learning-assisted fabrication: Bayesian optimization of laser-induced graphene patterning using in-situ raman analysis, Carbon, 167, 609-619 (2020) · doi:10.1016/j.carbon.2020.05.087 |
| [31] | Wen Q, Gao J, Song X, Sun L, Xu H, Zhu S (2019) Robuststl: A robust seasonal-trend decomposition algorithm for long time series. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 5409-5416 |
| [32] | Zaheer M, Guruganesh G, Dubey A, Ainslie J, Alberti C, Ontanon S, Pham P, Ravula A, Wang Q, Yang L, et al (2020) Big bird: transformers for longer sequences. arXiv preprint arXiv:2007.14062 |
| [33] | Zhu L, Laptev N (2017) Deep and confident prediction for time series at uber. In: 2017 IEEE International Conference on Data Mining Workshops (ICDMW), pp. 103-110. IEEE |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
