arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.19014cs.LGecon.EMstat.ML
收藏

SAGA:一种序列自适应的生成架构,用于多时间跨度概率预测的自适应时间符合预测

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

AI总结:

本文提出SAGA,一种用于不规则表格面板序列的解码器-only transformer,结合分割符合校准包装器,提供个体层面的预测区间,并保证有限样本边缘覆盖。SAGA在瑞典LISA登记处的纵向数据上训练,预测了1到30年的年度劳动收入,并通过蒙特卡洛方法汇总成现值寿命收入分布。与传统参数过程和表格和循环基线相比,SAGA在10年时间跨度上将连续排名概率分数减少了31.9%,在20年时间跨度上将平均绝对误差减少了37.7%。符合区间在边缘情况下覆盖率为0.4个百分点,在最差的人口子群体中为2.4个百分点。重建的寿命收入基尼系数为0.327,与部分观测的真实值0.341和GKOS估计值0.378相比。模型权重、校准表和合成等价数据集已发布,供在保护的SCB MONA环境中外的复制使用。

摘要:

用于财政部门和中央银行的微模拟模型依赖于参数过程来捕捉生命周期收入的寿命,这些过程只捕捉条件分布的一阶和二阶矩,忽略了长期非线性结构。我们提出SAGA,一种用于不规则表格面板序列的解码器-only transformer,结合分割符合校准包装器,提供个体层面的预测区间,并保证有限样本边缘覆盖。在1990年至2022年的纵向瑞典LISA登记处数据上训练,包含2,143,817个个体和61,284,903人年,模型预测了1到30年的年度劳动收入,并通过蒙特卡洛方法汇总成现值寿命收入分布。与传统参数过程和表格和循环基线相比,SAGA在10年时间跨度上将连续排名概率分数减少了31.9%,在20年时间跨度上将平均绝对误差减少了37.7%。符合区间在边缘情况下覆盖率为0.4个百分点,在最差的人口子群体中为2.4个百分点。重建的寿命收入基尼系数为0.327,与部分观测的真实值0.341和GKOS估计值0.378相比。模型权重、校准表和合成等价数据集已发布,供在保护的SCB MONA环境中外的复制使用。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑