SAGA: A Sequence-Adaptive Generative Architecture for Multi-Horizon Probabilistic Forecasting with Adaptive Temporal Conformal Prediction
Department of Economics, Stockholm University(斯德哥尔摩大学经济系);Institute of Social Sciences, Faculty of Economics and Administrative Sciences, Süleyman Demirel University(苏莱曼·德米雷尔大学社会科学学院,经济学与行政科学学院)
Gustav Olaf Yunus Laitinen-Fredriksson Lundström-Imanov, Hafize Gonca Cömert
备注:
14 pages, 3 figures, 12 tables, 5 appendices, 45 references. Submitted to IEEE TPAMI. Source code at https://github.com/olaflaitinen/saga (archived: doi:10.5281/zenodo.20260366). Synthetic equivalent dataset: doi:10.5281/zenodo.20260287. Empirical work conducted on the Swedish LISA register via SCB MONA (project SCB-MONA-2026-147); ethical approval Swedish Ethical Review Authority 2026-04127-01
Microsimulation models used by ministries of finance and central banks rely on parametric processes for lifetime earnings that capture only first and second moments of the conditional distribution and miss long-range nonlinear structure. We propose SAGA, a decoder-only transformer for irregular tabular panel sequences, paired with a split conformal calibration wrapper that delivers individual-level prediction intervals with finite-sample marginal coverage guarantees. Trained on the longitudinal Swedish LISA register over 1990 to 2022, comprising 2,143,817 individuals and 61,284,903 person-years, the model forecasts annual labor earnings at horizons of one to thirty years and aggregates them by Monte Carlo into present-discounted lifetime earnings distributions. Against the canonical Guvenen, Karahan, Ozkan, and Song parametric process and tabular and recurrent baselines, SAGA reduces continuous ranked probability score by 31.9 percent at the ten-year horizon and mean absolute error by 37.7 percent at the twenty-year horizon. Conformal intervals achieve nominal coverage to within 0.4 percentage points marginally and within 2.4 percentage points on the worst-case demographic subgroup. The reconstructed lifetime earnings Gini coefficient is 0.327 against the partially observed truth of 0.341 and the GKOS estimate of 0.378. Model weights, calibration tables, and a synthetic equivalent dataset are released for replication outside the protected SCB MONA environment.
Departments of Computer Science & Engineering and Data Science, New York University(纽约大学计算机科学与工程系和数据科学系);Department of Electrical Engineering and Computer Sciences, University of California, Berkeley(加州大学伯克利分校电气工程与计算机科学系)
Climate-Invariant Conformal Prediction Intervals for Multi-Horizon Solar and Wind Forecasting
Department of Computer Science and Engineering, Dr. B.R. Ambedkar National Institute of Technology Jalandhar, India(计算机科学与工程系,Dr. B.R. 阿姆贝卡尔国立技术学院贾兰德哈尔,印度)
Eletrcicité De France R&D(法国电力公司研发部);INRIA Sophia-Antipolis(法国国家信息与自动化研究所索菲亚-昂蒂波利斯分所);CMAP, Ecole Polytechnique, IP Paris(巴黎综合理工学院应用数学与概率中心(CMAP));FiME;IDESP;Eletrcicité De France R&D, Palaiseau, France(法国电力公司研发部(帕莱索));INRIA Sophia-Antipolis, Montpellier, France(法国国家信息与自动化研究所索菲亚-昂蒂波利斯分所(蒙彼利埃));CMAP, Ecole Polytechnique, IP Paris, Palaiseau, France(巴黎综合理工学院应用数学与概率中心(CMAP,帕莱索));FiME, Palaiseau, France(FiME(帕莱索));IDESP, Montpellier, France(IDESP(蒙彼利埃))
CoCopula: Conformal Calibration and Copula Aggregation for Reliable Renewable Energy Forecasting
NSF Artificial Intelligence Institute for Advances in Optimization(NSF人工智能优化研究所);H. Milton Stewart School of Industrial and Systems Engineering(H. Milton Stewart工业与系统工程学院);Georgia Institute of Technology(佐治亚理工学院)
Reliability-Centered Evaluation of Sparse Longitudinal CT Lesion-Size Forecasting with Conformal Interval Calibration and Gompertz-Inspired Regularization
Analyzing Uncertainty Quantification in Statistical and Deep Learning Models for Probabilistic Electricity Price Forecasting
Institute of Energy Engineering and Energy Economics, Ulm University of Applied Sciences(能源工程与经济学研究所,乌尔姆应用科学大学);Faculty of Mathematics and Economics, Ulm University(数学与经济学学院,乌尔姆大学);Faculty of Statistics, TU Dortmund University(统计学院,多特蒙德技术大学)
Extreme Conformal Prediction: Reliable Intervals for High-Impact Events
Research Institute for Statistics and Information Science, University of Geneva(日内瓦大学统计与信息科学研究院);Department of Industrial Engineering and Operations Research, Columbia University(哥伦比亚大学工业工程与运筹学系)
Conformal Convolution and Monte Carlo Meta-learners for Predictive Inference of Individual Treatment Effects
IDLab Department of Electronics and Information Systems Ghent University, Belgium(IDLab电子与信息系统系根特大学,比利时);IDLab Department of Electronics and Information Systems Ghent University - imec, Belgium(IDLab电子与信息系统系根特大学-imec,比利时);Biometrics Research Group Department of Morphology, Imaging, Orthopedics, Rehabilitation and Nutrition Ghent University, Belgium(生物医学研究组形态学、成像、骨科、康复与营养系根特大学,比利时)
A Gentle Introduction to Conformal Time Series Forecasting
Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);Royal Holloway, University of London(伦敦大学皇家霍洛威学院);Mohamed bin Zayed University of Artificial Intelligence(马尔代夫人工智能大学);University of Mons(蒙斯大学)
The Evolution of Probabilistic Price Forecasting Techniques: A Review of the Day-Ahead, Intra-Day, and Balancing Markets
SFI CRT in Artificial Intelligence, School of Computer Science \& IT, University College Cork, Ireland;SFI Insight Centre for Data Analytics, School of Computer Science \& IT, University College Cork, Ireland
ResCP: Reservoir Conformal Prediction for Time Series Forecasting
UiT the Arctic University of Norway(UiT北极大学);IDSIA USI-SUPSI, Università della Svizzera italiana(IDSIA瑞士联合大学);University of Oxford(牛津大学);NORCE Norwegian Research Centre AS(挪威研究机构)