{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:48:47Z","timestamp":1783702127726,"version":"3.55.0"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T00:00:00Z","timestamp":1717545600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Big Data"],"abstract":"<jats:p>Time series forecasting is an essential tool across numerous domains, yet traditional models often falter when faced with unilateral boundary conditions, where data is systematically overestimated or underestimated. This paper introduces a novel approach to the task of unilateral boundary time series forecasting. Our research bridges the gap in existing methods by proposing a specialized framework to accurately forecast within these skewed datasets. The cornerstone of our approach is the unilateral mean square error (UMSE), an asymmetric loss function that strategically addresses underestimation biases in training data, improving the precision of forecasts. We further enhance model performance through the implementation of a dual model structure that processes underestimated and accurately estimated data points separately, allowing for a nuanced analysis of the data trends. Additionally, feature reconstruction is employed to recapture obscured dynamics, ensuring a comprehensive understanding of the data. We demonstrate the effectiveness of our methods through extensive experimentation with LightGBM and GRU models across diverse datasets, showcasing superior accuracy and robustness in comparison to traditional models and existing methods. Our findings not only validate the efficacy of our approach but also reveal its model-independence and broad applicability. This work lays the groundwork for future research in this domain, opening new avenues for sophisticated analytical models in various industries where precise time series forecasting is crucial.<\/jats:p>","DOI":"10.3389\/fdata.2024.1376023","type":"journal-article","created":{"date-parts":[[2024,6,5]],"date-time":"2024-06-05T05:16:36Z","timestamp":1717564596000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Unilateral boundary time series forecasting"],"prefix":"10.3389","volume":"7","author":[{"given":"Chao-Min","family":"Chang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Te","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shou-De","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,6,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-306-47630-3","author":"Armstrong","year":"2001","journal-title":"Principles of Forecasting: A Handbook for Researchers and Practitioners, Vol. 30"},{"key":"B2","first-page":"193","article-title":"\u201cMemda: forecasting urban time series with memory-based drift adaptation,\u201d","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM '23","author":"Cai","year":"2023"},{"key":"B3","doi-asserted-by":"publisher","first-page":"6897","DOI":"10.1609\/aaai.v37i6.25844","article-title":"Estimating treatment effects from irregular time series observations with hidden confounders","volume":"37","author":"Cao","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B4","doi-asserted-by":"publisher","first-page":"6085","DOI":"10.1038\/s41598-018-24271-9","article-title":"Recurrent neural networks for multivariate time series with missing values","volume":"8","author":"Che","year":"2018","journal-title":"Sci. Rep"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.14838","article-title":"Calibration of time-series forecasting transformers: detecting and adapting context-driven distribution shift","author":"Chen","year":"2023","journal-title":"arXiv"},{"key":"B6","doi-asserted-by":"crossref","first-page":"1724","DOI":"10.3115\/v1\/D14-1179","article-title":"\u201cLearning phrase representations using RNN encoder-decoder for statistical machine translation,\u201d","volume-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Cho","year":"2014"},{"key":"B7","first-page":"900","article-title":"\u201cCombating distribution shift for accurate time series forecasting via hypernetworks,\u201d","volume-title":"2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS","author":"Duan","year":"2023"},{"key":"B8","doi-asserted-by":"publisher","first-page":"7522","DOI":"10.1609\/aaai.v37i6.25914","article-title":"Dish-ts: a general paradigm for alleviating distribution shift in time series forecasting","volume":"37","author":"Fan","year":"2023","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B9","doi-asserted-by":"publisher","first-page":"6639","DOI":"10.1609\/aaai.v36i6.20618","article-title":"Reinforcement learning based dynamic model combination for time series forecasting","volume":"36","author":"Fu","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B10","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1007\/s13201-012-0032-7","article-title":"Evaluating the accuracy of soil water sensors for irrigation scheduling to conserve freshwater","volume":"2","author":"Ganjegunte","year":"2012","journal-title":"Appl. Water Sci"},{"key":"B11","doi-asserted-by":"publisher","first-page":"4883","DOI":"10.5194\/amt-11-4883-2018","article-title":"The influence of humidity on the performance of a low-cost air particle mass sensor and the effect of atmospheric fog","volume":"11","author":"Jayaratne","year":"2018","journal-title":"Atmos. Meas. Tech"},{"key":"B12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2505821.2505826","article-title":"\u201cExploring human movements in singapore: a comparative analysis based on mobile phone and taxicab usages,\u201d","volume-title":"Proceedings of the 2nd ACM SIGKDD international workshop on urban computing","author":"Kang","year":"2013"},{"key":"B13","article-title":"\u201cLightgbm: a highly efficient gradient boosting decision tree,\u201d","volume-title":"Advances in neural information processing systems 30","author":"Ke","year":"2017"},{"key":"B14","article-title":"\u201cReversible instance normalization for accurate time-series forecasting against distribution shift,\u201d","author":"Kim","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"B15","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1145\/3209978.3210006","article-title":"\u201cModeling long-and short-term temporal patterns with deep neural networks,\u201d","author":"Lai","year":"2018","journal-title":"The 41st international ACM SIGIR conference on research"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1585","DOI":"10.5194\/amt-6-1585-2013","article-title":"A comparison of rainfall measurements from multiple instruments","volume":"6","author":"Liu","year":"2013","journal-title":"Atmos. Meas. Tech"},{"key":"B17","first-page":"9881","article-title":"Non-stationary transformers: exploring the stationarity in time series forecasting","volume":"35","author":"Liu","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B18","article-title":"\u201cAdaptive normalization for non-stationary time series forecasting: a temporal slice perspective,\u201d","author":"Liu","year":"2023","journal-title":"Thirty-seventh Conference on Neural Information Processing Systems"},{"key":"B19","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1002\/for.3980010202","article-title":"The accuracy of extrapolation (time series) methods: results of a forecasting competition","volume":"1","author":"Makridakis","year":"1982","journal-title":"J. Forecast"},{"key":"B20","article-title":"\u201cAttention is all you need,\u201d","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems 30 (NIPS 2017)"},{"key":"B21","article-title":"\u201cKoopman neural operator forecaster for time-series with temporal distributional shifts,\u201d","author":"Wang","year":"2023","journal-title":"The Eleventh International Conference on Learning Representations"},{"key":"B22","article-title":"\u201cHuber additive models for non-stationary time series analysis,\u201d","author":"Wang","year":"2022","journal-title":"International Conference on Learning Representations"},{"key":"B23","doi-asserted-by":"publisher","first-page":"2203","DOI":"10.1145\/3394486.3403271","article-title":"\u201cFast robuststl: efficient and robust seasonal-trend decomposition for time series with complex patterns,\u201d","author":"Wen","year":"2020","journal-title":"Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery"},{"key":"B24","doi-asserted-by":"publisher","first-page":"111549","DOI":"10.1016\/j.asoc.2024.111549","article-title":"Augmented support vector regression with an autoregressive process via an iterative procedure","volume":"158","author":"Wu","year":"2024","journal-title":"Appl. Soft Comput"},{"key":"B25","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1145\/3219819.3220066","article-title":"\u201cDeep censored learning of the winning price in the real time bidding,\u201d","author":"Wu","year":"2018","journal-title":"Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery"},{"key":"B26","doi-asserted-by":"publisher","first-page":"5658","DOI":"10.1109\/TSMC.2023.3272880","article-title":"Robust adaptive rescaled lncosh neural network regression toward time-series forecasting","volume":"53","author":"Yang","year":"2023","journal-title":"IEEE Trans. Syst. Man. Cybern. Syst"},{"key":"B27","first-page":"1336","article-title":"\u201cRobust probabilistic time series forecasting,\u201d","author":"Yoon","year":"2022","journal-title":"International Conference on Artificial Intelligence and Statistics"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1016\/j.ijforecast.2020.11.002","article-title":"Bayesian median autoregression for robust time series forecasting","volume":"37","author":"Zeng","year":"2021","journal-title":"Int. J. Forecast"},{"key":"B29","first-page":"3308","article-title":"\u201cA co-training approach for noisy time series learning,\u201d","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, CIKM '23","author":"Zhang","year":"2023"},{"key":"B30","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.neucom.2023.01.037","article-title":"Robust recurrent neural networks for time series forecasting","volume":"526","author":"Zhang","year":"2023","journal-title":"Neurocomputing"}],"container-title":["Frontiers in Big Data"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1376023\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T10:01:57Z","timestamp":1721383317000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fdata.2024.1376023\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,5]]},"references-count":30,"alternative-id":["10.3389\/fdata.2024.1376023"],"URL":"https:\/\/doi.org\/10.3389\/fdata.2024.1376023","relation":{},"ISSN":["2624-909X"],"issn-type":[{"value":"2624-909X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,5]]},"article-number":"1376023"}}