SAGA: A Sequence-Adaptive Generative Architecture for Multi-Horizon Probabilistic Forecasting with Adaptive Temporal Conformal Prediction

• URL: http://arxiv.org/abs/2605.19014v1
• Date: Mon, 18 May 2026 18:35:20 GMT
• Title: SAGA: A Sequence-Adaptive Generative Architecture for Multi-Horizon Probabilistic Forecasting with Adaptive Temporal Conformal Prediction
• Abstract summary: We propose SAGA, a decoder-only transformer that delivers individual-level prediction intervals with finite-sample marginal coverage guarantees.<n>We trained on the longitudinal Swedish LISA register over 1990 to 2022, comprising 2,143,817 individuals and 61,284,903 person-years.<n> 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.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CliffRank: A Dual-Branch Framework for Activity-Cliff Ranking Prediction [8.452103801866203]
  CliffRank trains two parallel predictors with mean squared error, a thresholded listwise loss, and Pairwise Preference Consistency (PPC)<n>On three antimicrobial peptide datasets, CliffRank with ESM2-t12 achieved the highest mean Spearman correlation of 0.5393 and mean Recall@50 of 21.4.<n>Future work should evaluate more targets and antimicrobial peptide systems, develop adaptive PPC schedules, and incorporate protein or membrane context when available.
  arXiv  Detail & Related papers  (2026-09-01T07:57:56Z)
• End-to-End Neural Shrinkage of Indefinite Pairwise Correlation Matrices for Small-Cap-Inclusive Portfolios [0.0]
  Small-cap-inclusive equity universes contain recently listed and intermittently traded securities, so enforcing a common look-back discards a substantial fraction of the available information.<n>We adapt a rotation-invariant neural covariance estimator to this setting.<n>We evaluate 26 expanding-window models from 2000 to 2025 on up to 1,500 U.S. equities in a closing-auction simulator with point-in-time selection, commissions, financing, corporate actions, and market impact.
  arXiv  Detail & Related papers  (2026-08-31T08:36:09Z)
• Explainable Machine Learning for Broadband Adoption Disparities: Tract-Level Prediction and SHAP-Based Factor Profiling [6.076837441966713]
  The United States has allocated approximately $65 billion through the Infrastructure Investment and Jobs Act for broadband expansion.<n>This paper presents an explainable machine learning framework for profiling broadband adoption disparities across 83,359 tracts nationwide.
  arXiv  Detail & Related papers  (2026-08-29T07:39:08Z)
• A time-series classification framework for individual-level absenteeism prediction under severe class imbalance [0.0]
  Staff absenteeism imposes substantial operational costs in high-demand work environments.<n>We propose a Time Series Classification framework that separates historical attendance sequences from future absence labels.
  arXiv  Detail & Related papers  (2026-06-30T11:44:52Z)
• RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting [83.06074370551887]
  A fixed context window is mismatched to the time-varying optimal look-back of non-stationary price processes.<n>We propose a Mixture-of-Experts framework designed to adaptively determine the temporal context for each input sample.<n> Experiments on cumulative log-return prediction (HS300, S&P500) and fund sales forecasting demonstrate that RAVEN achieves SOTA performances, improves Pearson correlation by 9.2% on HS300 and 20.2% on S&P500, and reduces MSE by 18.2% on fund sales forecasting.
  arXiv  Detail & Related papers  (2026-06-23T02:11:04Z)
• Knowledge Index of Noah's Ark [63.143852586221534]
  We introduce KINA, an 899-item benchmark across 261 fine-grained disciplines.<n>We prove a bonus-on-bar tournament weakly FOSD-dominates flat payment in released-review quality.<n>The top model, Gemini-3.1-Pro-Preview, reaches 53.17%, followed by Claude-Opus-4.6 at 49.92% and GPT-5.4 at 48.55%.
  arXiv  Detail & Related papers  (2026-06-03T17:06:49Z)
• SL-BiLEM: Structured Learnable Behavior-in-the-Loop Epidemic Modeling for Forecasting and Policy Evaluation [42.644852156101685]
  Epidemic forecasting faces a fundamental challenge: human behavior dynamically responds to disease spread.<n>We propose textbfSL-BiLEM (Structured Learnable Behavior-in-the-Loop Epidemic Model), leveraging physical constraints as regularization for robust extrapolation.
  arXiv  Detail & Related papers  (2026-05-26T08:46:04Z)
• Decoupled Conformal Optimisation: Efficient Prediction Sets via Independent Tuning and Calibration [20.21455697379946]
  We propose Decoupled Conformal optimisation (DCO) as a train-tune-calibrate design principle.<n>DCO uses an independent tuning split for efficiency-oriented structural selection and a fresh calibration split for the final conformal quantile.<n>We show that DCO tracks the nominal coverage level closely while often reducing average prediction-set size or interval width relative to PAC-style calibration.
  arXiv  Detail & Related papers  (2026-05-18T13:10:21Z)
• Exact Stiefel Optimization for Probabilistic PLS: Closed-Form Updates, Error Bounds, and Calibrated Uncertainty [5.844591976842085]
  We develop an end-to-end framework that combines noise pre-estimation, constrained likelihood optimization, and prediction calibration in one pipeline.<n>We extend the framework to sub-Gaussian settings via optional Gaussianization and provide closed-form standard errors through a block-structured Fisher analysis.
  arXiv  Detail & Related papers  (2026-05-12T06:38:12Z)
• Socio-Conformal Calibration in Complex Survey Data: Marginal Validity Is Not Enough for Subgroup Reliability [1.089614199781423]
  We study ordinal conformal prediction for five-level AI-attitude forecasting on the Pew American Trends Panel.<n>Standard conformal achieves nominal marginal coverage for all four base predictors but leaves weighted subgroup gaps of 13 percentage points.<n>For the strongest predictor (XGBoost), Mondrian worsens the fairness-efficiency trade-off.<n>A regularized comparator that shrinks group thresholds toward the global quantile mitigates this instability.
  arXiv  Detail & Related papers  (2026-05-07T01:10:48Z)
• Geometric Properties of the Voronoi Tessellation in Latent Semantic Manifolds of Large Language Models [0.0]
  Voronoi tessellation over representation manifold investigated on Qwen3.5-4B-Base.<n>We show that Voronoi tessellation is reshapable through margin refinement procedures.
  arXiv  Detail & Related papers  (2026-04-08T07:36:04Z)
• Fair regression under localized demographic parity constraints [9.082079838093371]
  We introduce a novel ($ell$, Z)-fair predictor, which imposes groupwise CDF constraints of the form F f |S=s (z m ) = $ell$ m for prescribed pairs.<n> Experiments on synthetic and real datasets illustrate an interpretable fairness-accuracy trade-off, enabling targeted corrections at decision-relevant quantiles or thresholds.
  arXiv  Detail & Related papers  (2026-03-26T09:21:05Z)
• Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking [51.56484100374058]
  We evaluate whether a fully automatic, purely feedback-driven ESN can serve as a competitive alternative to widely used statistical forecasting methods.<n>Forecast accuracy is measured using MASE and sMAPE and benchmarked against simple benchmarks like drift and seasonal naive and statistical models.
  arXiv  Detail & Related papers  (2026-02-03T16:01:22Z)
• AttentiveGRUAE: An Attention-Based GRU Autoencoder for Temporal Clustering and Behavioral Characterization of Depression from Wearable Data [46.262619407930266]
  We present AttentiveGRUAE, a novel attention-based gated recurrent unit (GRU) autoencoder designed for temporal clustering and prediction of outcome from longitudinal wearable data.<n>We evaluate AttentiveGRUAE on longitudinal sleep data from 372 participants (GLOBEM 2018-2019)<n>It demonstrates superior performance over baseline clustering, domain-aligned self-supervised, and ablated models in both clustering quality and depression classification.
  arXiv  Detail & Related papers  (2025-10-02T20:52:16Z)
• Certifiably Byzantine-Robust Federated Conformal Prediction [49.23374238798428]
  We introduce a novel framework Rob-FCP, which executes robust federated conformal prediction effectively countering malicious clients. We empirically demonstrate the robustness of Rob-FCP against diverse proportions of malicious clients under a variety of Byzantine attacks.
  arXiv  Detail & Related papers  (2024-06-04T04:43:30Z)
• Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity [55.29408396918968]
  We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification. Our contributions include both consistency and robustness by establishing top-$k$ consistency of LDR losses for multi-class classification. We propose a new adaptive LDR loss that automatically adapts the individualized temperature parameter to the noise degree of class label of each instance.
  arXiv  Detail & Related papers  (2021-12-30T00:27:30Z)
• Regularization methods for the short-term forecasting of the Italian electric load [77.34726150561087]
  The problem of forecasting the whole 24 profile of the Italian electric load is addressed as a multitask learning problem. The 96x96 matrix weights form a 96x96 matrix, that can be seen and displayed as a surface sampled on a square domain. Different regularization and sparsity approaches to reduce the degrees of freedom of the surface were explored, comparing the obtained forecasts with those of the Italian Transmission System Operator Terna.
  arXiv  Detail & Related papers  (2021-12-08T22:15:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.