Juyoung Ha , Sungwon Lee , Sooyeon Jeong , Doohee Chung
{"title":"高级时间序列需求预测方法:分解与深度学习混合模型","authors":"Juyoung Ha , Sungwon Lee , Sooyeon Jeong , Doohee Chung","doi":"10.1016/j.iswa.2025.200540","DOIUrl":null,"url":null,"abstract":"<div><div>Advancements in data science have increasingly focused on refining time-series predictive models for effective corporate management and demand forecasting. Traditional models often struggle to capture irregular patterns in time-series data. In this study, we employ a novel hybrid model integrating Ensemble Empirical Mode Decomposition (EEMD), Least Absolute Shrinkage and Selection Operator (LASSO), and Long Short-Term Memory (LSTM) networks to address these challenges. Our approach follows a structured pipeline: EEMD decomposes time-series data into ensemble Intrinsic Mode Functions (eIMFs) to reveal complex patterns, LASSO selects the most relevant features to optimize input variables, and LSTM captures long-term dependencies for accurate demand forecasting. We evaluate our model on real-world demand data from three industries (Office Product, Packaging Materials, and Pharmaceuticals), comparing it against ARIMAX, LightGBM, LSTM, and their EEMD-enhanced variants using NRMSE, NMAE, and R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>. Results show that integrating EEMD into baseline models reduces NRMSE by an average of 27.4%, while the additional incorporation of LASSO further improves performance, achieving a total reduction of 29.1%. Compared to the standalone LSTM model, our proposed EEMD-LASSO-LSTM model demonstrates a substantial NRMSE reduction of 51.2%, highlighting its superior predictive accuracy. This innovative combination of EEMD, LASSO, and LSTM enables our proposed method to effectively capture the irregular patterns of demand, a task that has been a significant hurdle for conventional forecasting methods. The integration of EEMD, LASSO, and LSTM marks a significant advancement in time-series predictive modeling, enhancing demand forecasting and informing strategic corporate decisions.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200540"},"PeriodicalIF":4.3000,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Methodology for advanced time series demand forecasting: A hybrid model of decomposition and deep learning\",\"authors\":\"Juyoung Ha , Sungwon Lee , Sooyeon Jeong , Doohee Chung\",\"doi\":\"10.1016/j.iswa.2025.200540\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Advancements in data science have increasingly focused on refining time-series predictive models for effective corporate management and demand forecasting. Traditional models often struggle to capture irregular patterns in time-series data. In this study, we employ a novel hybrid model integrating Ensemble Empirical Mode Decomposition (EEMD), Least Absolute Shrinkage and Selection Operator (LASSO), and Long Short-Term Memory (LSTM) networks to address these challenges. Our approach follows a structured pipeline: EEMD decomposes time-series data into ensemble Intrinsic Mode Functions (eIMFs) to reveal complex patterns, LASSO selects the most relevant features to optimize input variables, and LSTM captures long-term dependencies for accurate demand forecasting. We evaluate our model on real-world demand data from three industries (Office Product, Packaging Materials, and Pharmaceuticals), comparing it against ARIMAX, LightGBM, LSTM, and their EEMD-enhanced variants using NRMSE, NMAE, and R<span><math><msup><mrow></mrow><mrow><mn>2</mn></mrow></msup></math></span>. Results show that integrating EEMD into baseline models reduces NRMSE by an average of 27.4%, while the additional incorporation of LASSO further improves performance, achieving a total reduction of 29.1%. Compared to the standalone LSTM model, our proposed EEMD-LASSO-LSTM model demonstrates a substantial NRMSE reduction of 51.2%, highlighting its superior predictive accuracy. This innovative combination of EEMD, LASSO, and LSTM enables our proposed method to effectively capture the irregular patterns of demand, a task that has been a significant hurdle for conventional forecasting methods. The integration of EEMD, LASSO, and LSTM marks a significant advancement in time-series predictive modeling, enhancing demand forecasting and informing strategic corporate decisions.</div></div>\",\"PeriodicalId\":100684,\"journal\":{\"name\":\"Intelligent Systems with Applications\",\"volume\":\"27 \",\"pages\":\"Article 200540\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2025-07-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Intelligent Systems with Applications\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2667305325000663\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Intelligent Systems with Applications","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2667305325000663","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Methodology for advanced time series demand forecasting: A hybrid model of decomposition and deep learning
Advancements in data science have increasingly focused on refining time-series predictive models for effective corporate management and demand forecasting. Traditional models often struggle to capture irregular patterns in time-series data. In this study, we employ a novel hybrid model integrating Ensemble Empirical Mode Decomposition (EEMD), Least Absolute Shrinkage and Selection Operator (LASSO), and Long Short-Term Memory (LSTM) networks to address these challenges. Our approach follows a structured pipeline: EEMD decomposes time-series data into ensemble Intrinsic Mode Functions (eIMFs) to reveal complex patterns, LASSO selects the most relevant features to optimize input variables, and LSTM captures long-term dependencies for accurate demand forecasting. We evaluate our model on real-world demand data from three industries (Office Product, Packaging Materials, and Pharmaceuticals), comparing it against ARIMAX, LightGBM, LSTM, and their EEMD-enhanced variants using NRMSE, NMAE, and R. Results show that integrating EEMD into baseline models reduces NRMSE by an average of 27.4%, while the additional incorporation of LASSO further improves performance, achieving a total reduction of 29.1%. Compared to the standalone LSTM model, our proposed EEMD-LASSO-LSTM model demonstrates a substantial NRMSE reduction of 51.2%, highlighting its superior predictive accuracy. This innovative combination of EEMD, LASSO, and LSTM enables our proposed method to effectively capture the irregular patterns of demand, a task that has been a significant hurdle for conventional forecasting methods. The integration of EEMD, LASSO, and LSTM marks a significant advancement in time-series predictive modeling, enhancing demand forecasting and informing strategic corporate decisions.