Mengfei Cao

Kin G. Olivares, Geoffrey Négiar, Ruijun Ma et al. · berkeley

Obtaining accurate probabilistic forecasts is an operational challenge in many applications, such as energy management, climate forecasting, supply chain planning, and resource allocation. Many of these applications present a natural hierarchical structure over the forecasted quantities; and forecasting systems that adhere to this hierarchical structure are said to be coherent. Furthermore, operational planning benefits from the accuracy at all levels of the aggregation hierarchy. However, building accurate and coherent forecasting systems is challenging: classic multivariate time series tools and neural network methods are still being adapted for this purpose. In this paper, we augment an MQForecaster neural network architecture with a modified multivariate Gaussian factor model that achieves coherence by construction. The factor model samples can be differentiated with respect to the model parameters, allowing optimization on arbitrary differentiable learning objectives that align with the forecasting system's goals, including quantile loss and the scaled Continuous Ranked Probability Score (CRPS). We call our method the Coherent Learning Objective Reparametrization Neural Network (CLOVER). In comparison to state-of-the-art coherent forecasting methods, CLOVER achieves significant improvements in scaled CRPS forecast accuracy, with average gains of 15%, as measured on six publicly-available datasets.

Andres Potapczynski, Ravi Kiran Selvam, Tatiana Konstantinova et al.

In many time series forecasting settings, the target time series is accompanied by exogenous covariates, such as promotions and prices in retail demand; temperature in energy load; calendar and holiday indicators for traffic or sales; and grid load or fuel costs in electricity pricing. Ignoring these exogenous signals can substantially degrade forecasting accuracy, particularly when they drive spikes, discontinuities, or regime and phase changes in the target series. Most current time series foundation models (e.g., Chronos, Sundial, TimesFM, TimeMoE, TimeLLM, and LagLlama) ignore exogenous covariates and make forecasts solely from the numerical time series history, thereby limiting their performance. In this paper, we develop ApolloPFN, a prior-data fitted network (PFN) that is time-aware (unlike prior PFNs) and that natively incorporates exogenous covariates (unlike prior univariate forecasters). Our design introduces two major advances: (i) a synthetic data generation procedure tailored to resolve the failure modes that arise when tabular (non-temporal) PFNs are applied to time series; and (ii) time-aware architectural modifications that embed inductive biases needed to exploit the time series context. We demonstrate that ApolloPFN achieves state-of-the-art results across benchmarks, such as M5 and electric price forecasting, that contain exogenous information.

Boris N. Oreshkin, Mayank Jauhari, Ravi Kiran Selvam et al.

Zero-shot time-series forecasting holds great promise, but is still in its infancy, hindered by limited and biased data corpora, leakage-prone evaluation, and privacy and licensing constraints. Motivated by these challenges, we propose the first practical univariate time series simulation pipeline which is simultaneously fast enough for on-the-fly data generation and enables notable zero-shot forecasting performance on M-Series and GiftEval benchmarks that capture trend/seasonality/intermittency patterns, typical of industrial forecasting applications across a variety of domains. Our simulator, which we call SarSim0 (SARIMA Simulator for Zero-Shot Forecasting), is based off of a seasonal autoregressive integrated moving average (SARIMA) model as its core data source. Due to instability in the autoregressive component, naive SARIMA simulation often leads to unusable paths. Instead, we follow a three-step procedure: (1) we sample well-behaved trajectories from its characteristic polynomial stability region; (2) we introduce a superposition scheme that combines multiple paths into rich multi-seasonality traces; and (3) we add rate-based heavy-tailed noise models to capture burstiness and intermittency alongside seasonalities and trends. SarSim0 is orders of magnitude faster than kernel-based generators, and it enables training on circa 1B unique purely simulated series, generated on the fly; after which well-established neural network backbones exhibit strong zero-shot generalization, surpassing strong statistical forecasters and recent foundation baselines, while operating under strict zero-shot protocol. Notably, on GiftEval we observe a "student-beats-teacher" effect: models trained on our simulations exceed the forecasting accuracy of the AutoARIMA generating processes.

Kin G. Olivares, Malcolm Wolff, Tatiana Konstantinova et al.

Cross-frequency transfer learning (CFTL) has emerged as a popular framework for curating large-scale time series datasets to pre-train foundation forecasting models (FFMs). Although CFTL has shown promise, current benchmarking practices fall short of accurately assessing its performance. This shortcoming stems from many factors: an over-reliance on small-scale evaluation datasets; inadequate treatment of sample size when computing summary statistics; reporting of suboptimal statistical models; and failing to account for non-negligible risks of overlap between pre-training and test datasets. To address these limitations, we introduce a unified reimplementation of widely-adopted neural forecasting networks, adapting them for the CFTL setup; we pre-train only on proprietary and synthetic data, being careful to prevent test leakage; and we evaluate on 15 large, diverse public forecast competition datasets. Our empirical analysis reveals that statistical models' accuracy is frequently underreported. Notably, we confirm that statistical models and their ensembles consistently outperform existing FFMs by more than 8.2% in sCRPS, and by more than 20% MASE, across datasets. However, we also find that synthetic dataset pre-training does improve the accuracy of a FFM by 7% percent.

Willa Potosnak, Malcolm Wolff, Boris Oreshkin et al.

While accuracy is a critical requirement for time series forecasting models, an equally important (yet often overlooked) desideratum is forecast stability across forecast creation dates (FCDs). Even highly accurate models can produce erratic revisions between FCDs, undermining stakeholder trust and disrupting downstream decision-making. To improve forecast stability, models like MQCNN, MQT, and SPADE employ a little-known but highly effective technique: forking-sequences. Unlike standard statistical and neural forecasting methods that treat each FCD independently, the forking-sequences method jointly encodes and decodes the entire time series across all FCDs, in a way mirroring time series cross-validation. Since forking sequences remains largely unknown in the broader neural forecasting community, in this work, we formalize the forking-sequences approach, and we make a case for its broader adoption. We demonstrate three key benefits of forking-sequences: (i) more stable and consistent gradient updates during training; (ii) reduced forecast variance through ensembling; and (iii) improved inference computational efficiency. We validate forking-sequences' benefits using 16 datasets from the M1, M3, M4, and Tourism competitions, showing improvements in forecast percentage change stability of 28.8%, 28.8%, 37.9%, and 31.3%, and 8.8%, on average, for MLP, RNN, LSTM, CNN, and Transformer-based architectures, respectively.

Malcolm Wolff, Matthew Li, Ravi Kiran Selvam et al.

Despite significant advancements in time series forecasting, accurate modeling of time series with strong heterogeneity in magnitude and/or sparsity patterns remains challenging for state-of-the-art deep learning architectures. We identify several factors that lead existing models to systematically underperform on low-magnitude and sparse time series, including loss functions with implicit biases toward high-magnitude series, training-time sampling methods, and limitations of time series encoding methods. SPADE-S is a robust forecasting architecture that significantly reduces magnitude- and sparsity-based systematic biases and improves overall prediction accuracy. Empirical results demonstrate that SPADE-S outperforms existing state-of-the-art approaches across a diverse set of use cases in demand forecasting. In particular, we show that, depending on the quantile forecast and magnitude of the series, SPADE-S can improve forecast accuracy by up to 15%. This results in P90 overall forecast accuracy gains of 2.21%, 6.58%, and 4.28%, and P50 forecast accuracy gains of 0.92%, 0.77%, and 1.95%, respectively, for each of three distinct datasets, ranging from 3 million to 700 million series, from a large online retailer.

Kin G. Olivares, O. Nganba Meetei, Ruijun Ma et al.

Hierarchical forecasting problems arise when time series have a natural group structure, and predictions at multiple levels of aggregation and disaggregation across the groups are needed. In such problems, it is often desired to satisfy the aggregation constraints in a given hierarchy, referred to as hierarchical coherence in the literature. Maintaining coherence while producing accurate forecasts can be a challenging problem, especially in the case of probabilistic forecasting. We present a novel method capable of accurate and coherent probabilistic forecasts for time series when reliable hierarchical information is present. We call it Deep Poisson Mixture Network (DPMN). It relies on the combination of neural networks and a statistical model for the joint distribution of the hierarchical multivariate time series structure. By construction, the model guarantees hierarchical coherence and provides simple rules for aggregation and disaggregation of the predictive distributions. We perform an extensive empirical evaluation comparing the DPMN to other state-of-the-art methods which produce hierarchically coherent probabilistic forecasts on multiple public datasets. Comparing to existing coherent probabilistic models, we obtain a relative improvement in the overall Continuous Ranked Probability Score (CRPS) of 11.8% on Australian domestic tourism data, and 8.1% on the Favorita grocery sales dataset, where time series are grouped with geographical hierarchies or travel intent hierarchies. For San Francisco Bay Area highway traffic, where the series' hierarchical structure is randomly assigned, and their correlations are less informative, our method does not show significant performance differences over statistical baselines.