FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting

• URL: http://arxiv.org/abs/2606.08896v1
• Date: Mon, 08 Jun 2026 00:47:58 GMT
• Title: FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting
• Abstract summary: We study forecastability-aware expert routing, learning how data characteristics determine the suitability of forecasting experts.<n>We propose method, a sparse mixture-of-experts framework that represents each series with a multidimensional forecastability fingerprint.<n>On the industrial dataset with 5,000+ machines and 60M+ transactions, method Top-2 reduces MSE by 12.4% over the strongest single expert.
• Score: 13.22770189732018
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large-scale retail and industrial forecasting systems contain many heterogeneous time series whose lifecycle, sparsity, volatility, seasonality, spectral patterns, and contextual sensitivity differ substantially. A single forecasting model rarely performs well across all regimes, while dense ensembles increase inference cost and provide limited insight into expert suitability. This paper studies forecastability-aware expert routing: learning how data characteristics determine the suitability of forecasting experts. We propose \method{}, a sparse mixture-of-experts framework that represents each series with a multidimensional forecastability fingerprint, mines expert-suitability targets from validation performance, and trains a cost-aware sparse router to activate a small budgeted set of experts for each series. Using a production-scale vending-machine sales dataset from Shandong New Beiyang (SNBC), where the forecasting component has been integrated into the replenishment-planning pipeline, together with public retail benchmarks, we show that expert suitability varies systematically across data regimes. On the industrial dataset with 5,000+ machines and 60M+ transactions, \method{} Top-2 reduces MSE by 12.4\% over the strongest single expert, LightGBM, while executing 1.92 experts per series on average. The deployed component produces demand forecasts, while inventory-oriented gains are estimated by an offline replay simulator under a fixed replenishment policy rather than by online intervention. The framework turns heterogeneous sales forecasting from heuristic model selection into data mining of forecastability patterns and expert specialization. Code is available at https://github.com/hit636/FAME

Related papers

• Are Gradient Boosting Models Suitable for Intermittent Demand Forecasting? [0.6531546527140474]
  This paper explores the potential of gradient boosting models to improve forecasting performance.<n>We evaluate statistical, specialized, machine learning, and ensemble approaches across multiple datasets.
  arXiv  Detail & Related papers  (2026-09-13T18:23:23Z)
• MetaCaster: Meta-Harness-Optimized Agent for End-to-End Few-Shot Learning of Lightweight Time Series Forecasters [86.78565015172455]
  Time series forecasting (TSF) is evolving toward multimodal and agentic settings.<n>We propose MetaCaster, a meta-harness-optimized multi-agent framework to automatically train specialized lightweight forecasters.<n>Our work highlights a new TSF paradigm in which agents act not as forecasters but as intermediary engineers.
  arXiv  Detail & Related papers  (2026-08-24T16:40:25Z)
• 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)
• ARIMA_PLUS: Large-scale, Accurate, Automatic and Interpretable In-Database Time Series Forecasting and Anomaly Detection in Google BigQuery [5.170341372465115]
  Time series forecasting and anomaly detection are common tasks for practitioners in industries such as retail, manufacturing, advertising and energy.<n>We present ARIMA_PLUS, a novel framework to overcome these two challenges by a unique combination of (a) accurate and interpretable time series models and (b) scalable and fully managed system infrastructure.
  arXiv  Detail & Related papers  (2025-10-28T14:18:50Z)
• TAT: Temporal-Aligned Transformer for Multi-Horizon Peak Demand Forecasting [51.37167759339485]
  We propose Temporal-Aligned Transformer (TAT), a multi-horizon forecaster leveraging apriori-known context variables for improving predictive performance.<n>Our model consists of an encoder and decoder, both embedded with a novel Temporal Alignment Attention (TAA) designed to learn context-dependent alignment for peak demand forecasting.<n>We demonstrate that TAT brings up to 30% accuracy on peak demand forecasting while maintaining competitive overall performance compared to other state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-07-14T14:51:24Z)
• When Does Multimodality Lead to Better Time Series Forecasting? [96.26052272121615]
  We investigate whether and under what conditions such multimodal integration consistently yields gains.<n>Our findings reveal that the benefits of multimodality are highly condition-dependent.<n>Our study offers a rigorous, quantitative foundation for understanding when multimodality can be expected to aid forecasting tasks.
  arXiv  Detail & Related papers  (2025-06-20T23:55:56Z)
• Tackling Data Heterogeneity in Federated Time Series Forecasting [61.021413959988216]
  Time series forecasting plays a critical role in various real-world applications, including energy consumption prediction, disease transmission monitoring, and weather forecasting. Most existing methods rely on a centralized training paradigm, where large amounts of data are collected from distributed devices to a central cloud server. We propose a novel framework, Fed-TREND, to address data heterogeneity by generating informative synthetic data as auxiliary knowledge carriers.
  arXiv  Detail & Related papers  (2024-11-24T04:56:45Z)
• Mixture of Efficient Diffusion Experts Through Automatic Interval and Sub-Network Selection [63.96018203905272]
  We propose to reduce the sampling cost by pruning a pretrained diffusion model into a mixture of efficient experts. We demonstrate the effectiveness of our method, DiffPruning, across several datasets.
  arXiv  Detail & Related papers  (2024-09-23T21:27:26Z)
• F-FOMAML: GNN-Enhanced Meta-Learning for Peak Period Demand Forecasting with Proxy Data [65.6499834212641]
  We formulate the demand prediction as a meta-learning problem and develop the Feature-based First-Order Model-Agnostic Meta-Learning (F-FOMAML) algorithm. By considering domain similarities through task-specific metadata, our model improved generalization, where the excess risk decreases as the number of training tasks increases. Compared to existing state-of-the-art models, our method demonstrates a notable improvement in demand prediction accuracy, reducing the Mean Absolute Error by 26.24% on an internal vending machine dataset and by 1.04% on the publicly accessible JD.com dataset.
  arXiv  Detail & Related papers  (2024-06-23T21:28:50Z)
• Optimizing Sales Forecasts through Automated Integration of Market Indicators [0.0]
  This work investigates the potential of data-driven techniques to automatically select and integrate market indicators for improving customer demand predictions. By adopting an exploratory methodology, we integrate macroeconomic time series, such as national GDP growth, into textitNeural Prophet and textitSARIMAX forecasting models. It could be shown that forecasts can be significantly enhanced by incorporating external information.
  arXiv  Detail & Related papers  (2024-05-15T08:11:41Z)
• Probabilistic Forecasting of Real-Time Electricity Market Signals via Interpretable Generative AI [41.99446024585741]
  We present WIAE-GPF, a Weak Innovation AutoEncoder-based Generative Probabilistic Forecasting architecture. A novel learning algorithm with structural convergence guarantees is proposed, ensuring that the generated forecast samples match the ground truth conditional probability distribution.
  arXiv  Detail & Related papers  (2024-03-09T00:41:30Z)
• AMEND: A Mixture of Experts Framework for Long-tailed Trajectory Prediction [6.724750970258851]
  We propose a modular model-agnostic framework for trajectory prediction. Each expert is trained with a specialized skill with respect to a particular part of the data. To produce predictions, we utilise a router network that selects the best expert by generating relative confidence scores.
  arXiv  Detail & Related papers  (2024-02-13T02:43:41Z)
• Expert Aggregation for Financial Forecasting [0.0]
  Online aggregation of experts combine the forecasts of a finite set of models in a single approach. Online mixture of experts leads to attractive portfolio performances even in environments characterised by non-stationarity. Extensions to expert and aggregation specialisations are also proposed to improve the overall mixture on a family of portfolio evaluation metrics.
  arXiv  Detail & Related papers  (2021-11-25T10:43:58Z)

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.