arXiv:2608. 12251v1 Announce Type: cross Abstract: Financial volatility is regime dependent, yet incorporating regime information into neural networks can also destabilize training.
arXiv:2510. 04487v5 Announce Type: replace Abstract: While accuracy is a critical requirement for time series forecasting, an equally important desideratum is reasonable forecast volatility across forecast creation dates (FCDs).
MoFE is a deep learning framework that combines Fourier Neural Operators with a Mixture-of-Experts architecture to forecast cryptocurrency prices. It models volatility as a mix of multi-frequency components—including fundamental growth, mining costs, halving events, and market sentiment—using adaptive FNO and convolutional experts. Experiments on Bitcoin data from 2020 to 2025 show MoFE outperforms existing models in short‑term horizons, reducing phase‑lag errors and improving directional accuracy and information coefficient, which translates into higher Sharpe ratios in simulated trading.
arXiv:2606. 27688v1 Announce Type: cross Abstract: In financial forecasting, predictive performance depends not only on which model is trained, but also on how the trained model is deployed.
arXiv:2606. 24062v1 Announce Type: cross Abstract: Financial time series forecasting presents structural challenges absent from standard benchmarks.
The paper introduces an adaptive Mixture-of-Experts (MoE) framework for time series forecasting that incorporates expert-specific losses to give each expert a direct learning signal independent of gating weights. The overall objective combines base forecasting loss with these expert losses, encouraging experts to specialize on different temporal segments. A partial online learning strategy is added for efficient incremental updates, and experiments on economic, tourism, and energy datasets show the method outperforms state‑of‑the‑art neural models and foundation models, with ablation studies confirming the benefit of expert loss integration.
arXiv:2606. 03184v1 Announce Type: cross Abstract: Financial forecasting is difficult due to low signal-to-noise ratios, latent factors, heavy tails, regime shifts, and jumps.
VertiFuseX is a hybrid LSTM architecture that fuses multi‑scale temporal representations at the penultimate layer, stacking features from LSTM, Bi‑LSTM, and St‑LSTM branches and a parallel DNN stream. On 15 years of global equity index data, it reduces MAPE by 30‑54% and improves MAE and RMSE by over 40% compared to LSTM baselines, outperforming seven state‑of‑the‑art models across 33 metric‑dataset comparisons. The model is lightweight (675k parameters, 2.6 MB footprint) with 1.5 ms/sample inference latency and demonstrates robust, interpretable forecasting with reduced drawdowns in algorithmic trading simulations.
arXiv:2606. 08896v1 Announce Type: new 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.
arXiv:2607. 22491v1 Announce Type: new Abstract: Volatility forecasting is dominated by persistence and measurement noise, leaving limited residual structure for nonlinear models to exploit.
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.
The paper introduces the Finance‑Aware Graph Spatio‑Temporal Network (FA‑GSTN) for forecasting realized volatility by treating the implied volatility surface as a dynamic graph. Nodes represent grid points on the surface, with edges capturing adaptive intra‑day spatial and explicit inter‑day temporal relationships, while finance‑aware node features (e.g., option Greeks) and a multi‑scale temporal smoothing gate address high‑frequency noise. Experiments on a large equity options dataset show FA‑GSTN achieves state‑of‑the‑art predictive accuracy (R² up to 0.473) and outperforms Vision Transformer baselines even with only one year of training data, demonstrating robustness during market stress.
arXiv:2608. 19394v1 Announce Type: cross Abstract: We introduce Deep-MKV-TS, a path-dependent McKean-Vlasov framework for financial scenario generation.