RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting

• URL: http://arxiv.org/abs/2606.24062v1
• Date: Tue, 23 Jun 2026 02:11:04 GMT
• Title: RAVEN: A Regime-Aware Variable-context Expert Network for Financial Time Series Forecasting
• Abstract summary: 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.
• Score: 83.06074370551887
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Financial time series forecasting presents structural challenges absent from standard benchmarks. Log-returns are non-stationary, exhibit exceptionally low signal-to-noise (SNR) ratios, and are governed by regime-dependent temporal dependencies. We identify a key limitation of state-of-the-art (SOTA) time series models in financial settings. A fixed context window is mismatched to the time-varying optimal look-back of non-stationary price processes. We propose the Regime-Aware Variable-context Expert Network (RAVEN), a Mixture-of-Experts framework designed to adaptively determine the temporal context for each input sample. Instead of relying on a fixed look-back horizon, RAVEN constructs a hierarchy of nested contiguous windows whose lengths are determined by the data itself. Specifically, RAVEN scores patches by learned importance in reverse chronological order and applies the Cumulative Importance Thresholding (CIT) mechanism to derive nested prefix windows, each routed to a scale-specialized expert. A Global Compressed Representation (GCR) branch runs in parallel over the full context, preserving global temporal coherence that local experts cannot guarantee. Because the nested routing induces structured overlap among expert inputs, we introduce a Correlation-Aware Weighting (CAW) to align variable-length expert outputs and penalize pairwise cosine similarity prior to aggregation. 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, while achieving the best results in 14 of 16 metrics on four PEMS traffic benchmarks.

Related papers

• Hierarchical Exponential-Gaussian Mixtures for Watch-Time Distribution Prediction [74.05279072166697]
  Exponential-Gaussian Mixture Network (EGMN) models the full conditional WT distribution.<n>EGMN is vulnerable to variance collapse, component redundancy, and inactive components.<n>We propose a Hierarchical Exponential-Gaussian Mixture (HEGM) model that addresses these failure modes.
  arXiv  Detail & Related papers  (2026-08-24T15:06:18Z)
• DecoVAE: a Lightweight Interpretable Trend-Seasonal VAE Framework for Efficient Probabilistic Time Series Forecasting [43.38565681834944]
  We propose DecoVAE, a lightweight interpretable trend-seasonal VAE framework.<n>It decomposes time series into trend and seasonal components by applying domain-specific inductive biases.<n>It consistently outperforms strong baselines in seven real-world benchmarks.
  arXiv  Detail & Related papers  (2026-08-20T13:51:07Z)
• F2STNet: Fair and Federated Spectral-Temporal Modeling for Graph Forecasting [14.982972903182896]
  F$2$STNet is a federated forecasting framework that combines truncated graph-Fourier features, a lightweight diagonal state-space temporal encoder, and graph convolution.<n>Experiments on PeMS04, HZMetro, and KnowAir show favorable forecasting accuracy relative to the evaluated baselines.
  arXiv  Detail & Related papers  (2026-08-10T03:29:15Z)
• Susceptible Reservoir Architectures for Regime-Conditional Volatility Forecasting [0.0]
  We introduce Susceptible Architectures (SUSA), a reservoir-design principle for volatility forecasting, and its two concrete implementations.<n>We evaluate models on 16 U.S. equity and exchange-traded-fund series using three disjoint chronological training, validation, and test folds.<n>The proposed models perform competitively with GARCH, achieving statistically significant QLIKE improvements for specific assets.
  arXiv  Detail & Related papers  (2026-07-24T17:03:08Z)
• Improving Coherence in Hierarchical Time Series Forecasting using Structured Temporal Fusion [0.0]
  Hierarchical Temporal Fusion (HTF) integrates structured hierarchical embeddings with a coherence-aware loss function to ensure consistent forecasts across all levels of a hierarchy.<n>We evaluate HTF on two publicly available benchmark datasets: the M5 Walmart forecasting dataset and a publicly available hierarchical energy consumption dataset.
  arXiv  Detail & Related papers  (2026-06-26T19:11:40Z)
• FAME: Forecastability-Aware Mixture of Experts for Heterogeneous Time Series Forecasting [13.22770189732018]
  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.
  arXiv  Detail & Related papers  (2026-06-08T00:47:58Z)
• Time-Aware Prior Fitted Networks for Zero-Shot Forecasting with Exogenous Variables [59.37476887007663]
  We develop ApolloPFN, a prior-data fitted network (PFN) that is time-aware (unlike prior PFNs)<n>Our design introduces two major advances: (i) a synthetic data generation procedure tailored to resolve the failure modes that arise when PFNs are applied to time series; and (ii) time-aware architectural modifications that embed inductive biases needed to exploit the time series context.
  arXiv  Detail & Related papers  (2026-03-16T18:33:23Z)
• It's TIME: Towards the Next Generation of Time Series Forecasting Benchmarks [87.7937890373758]
  Time series foundation models (TSFMs) are revolutionizing the forecasting landscape from specific dataset modeling to generalizable task evaluation.<n>We introduce TIME, a next-generation task-centric benchmark comprising 50 fresh datasets and 98 forecasting tasks.<n>We propose a novel pattern-level evaluation perspective that moves beyond traditional dataset-level evaluations based on static meta labels.
  arXiv  Detail & Related papers  (2026-02-12T16:31:01Z)
• 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)
• EVEREST: An Evidential, Tail-Aware Transformer for Rare-Event Time-Series Forecasting [4.551615447454767]
  EVEREST is a transformer-based architecture for probabilistic rare-event forecasting.<n>It delivers calibrated predictions and tail-aware risk estimation.<n>It is applicable to high-stakes domains such as industrial monitoring, weather, and satellite diagnostics.
  arXiv  Detail & Related papers  (2026-01-26T23:15:20Z)
• PRISM: A hierarchical multiscale approach for time series forecasting [42.91635448262212]
  Real-world time series contain both global trends, local fine-grained structure, and features on multiple scales in between.<n>We present a new forecasting method, PRISM, that addresses this challenge through a learnable tree-based partitioning of the signal.<n> Experiments across benchmark datasets show that our method outperforms state-of-the-art methods for forecasting.
  arXiv  Detail & Related papers  (2025-12-31T14:51:12Z)
• Temporal Conformal Prediction (TCP): A Distribution-Free Statistical and Machine Learning Framework for Adaptive Risk Forecasting [0.0]
  TCP is a distribution-free framework for constructing well-calibrated prediction intervals in nonstationary time series.<n> TCP couples a modern quantile forecaster with a split-conformal calibration layer on a rolling window.<n>Crisis-window visualizations show TCP/ TCP-RM expanding and then contracting their interval bands promptly as volatility spikes and recedes.
  arXiv  Detail & Related papers  (2025-07-07T20:44:31Z)
• Forecasting Foreign Exchange Rates With Parameter-Free Regression Networks Tuned By Bayesian Optimization [4.642930060629522]
  The article is concerned with the problem of multi-step financial time series forecasting of Foreign Exchange (FX) rates. To address this problem, we introduce a parameter-free regression network termed RegPred Net.
  arXiv  Detail & Related papers  (2022-04-26T13:32:50Z)
• Cluster-and-Conquer: A Framework For Time-Series Forecasting [94.63501563413725]
  We propose a three-stage framework for forecasting high-dimensional time-series data. Our framework is highly general, allowing for any time-series forecasting and clustering method to be used in each step. When instantiated with simple linear autoregressive models, we are able to achieve state-of-the-art results on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-26T20:41:19Z)

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.