slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
volatility-regime-research
An empirical study on cross-regime volatility forecasting for the KOSPI200, demonstrating that a two-parameter mean-reversion anchor generalizes across volatility regimes while XGBoost, Random Forests, and Transformers all fail with negative out-of-distribution R².
Stars
3
7-day growth
No data
Forks
0
Open issues
0
License
MIT
Last updated
2026-07-29
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It challenges the prevailing assumption that more complex models generalize better, providing strong evidence that embedding financial theory (a simple anchor) dramatically outperforms flexible learners in out-of-distribution settings, and reveals that in-regime accuracy is uninformative about cross-regime robustness.
Who it is for
- Financial machine learning researchers
- Quantitative analysts and volatility forecasters
- Practitioners in portfolio risk management
- Machine learning robustness researchers
Use cases
- Designing robust volatility models that retain skill under regime shifts
- Stress-testing forecasting models by evaluating them on clearly separated volatility regimes
- Benchmarking the generalization of ML models against theory-driven baselines in finance
- Developing physics-informed neural networks with additive architectural components
Strengths
- Clear experimental setup with controlled regime transitions and leakage control (42-day embargo)
- Reproducible code, data pipeline, and shared CSV ensuring byte-identical inputs across all models
- Comprehensive comparison of six models with block-bootstrap confidence intervals on R² differences
- Strong empirical evidence that structure, not capacity, is the key to cross-regime generalization
Considerations
- The anchor's advantage relies on trailing observed volatility, meaning it adapts quickly after a shift but cannot anticipate it
- The study covers only a single index (KOSPI200); generalization to other markets is future work
- No model can predict regime changes; the anchor merely mitigates cross-regime failure rather than solving it
README quick start
Cross-Regime Robustness of Volatility Forecasting
Why a two-parameter mean-reversion anchor generalizes where XGBoost, Random Forests, and Transformers fail.
An empirical study of out-of-distribution robustness in volatility forecasting on the KOSPI200. Six models are compared on identical data under controlled regime transitions, testing whether learned models retain forecasting skill when the volatility level shifts — and whether embedding financial theory into a neural network repairs the failure.
Status: Undergraduate research project. Preprint + code archived for the record. If you use this work, please cite via the DOI in
CITATION.cff(see below).
TL;DR — the main finding
Cross-regime volatility generalization is a problem of structure, not capacity. Flexible learners do not fail to find a signal; they discard transferable structure that a two-parameter formula retains, in exchange for regime-specific fit.
Cross-regime R² (train on one volatility regime, test on another):
| Experiment | XGBoost | Random Forest | Transformer | soft-PINN | additive-PINN | anchor |
|---|---|---|---|---|---|---|
| E1 (low→high) | −1.15 | −1.14 | −1.11 | −1.12 | 0.68 | 0.71 |
| E2 (high→low) | −22.9 | −27.2 | −22.2 | −10.1 | 0.70 | 0.76 |
| E3 (mid→high) | −0.80 | −0.78 | −0.67 | −0.76 | 0.59 | 0.57 |
| E4 (mid→low) | −3.75 | −5.77 | −2.55 | −4.41 | −0.40 | −0.96 |
| E5 (bridge→mid) | −4.72 | −10.5 | −5.02 | −3.47 | 0.32 | 0.69 |
All four data-driven models score negative cross-regime R² everywhere (Crisis Robustness Score = 0.00). A two-parameter closed-form mean-reversion anchor, with no training, achieves positive R² on four of five experiments.
Key results
- Data-driven models: strong in-regime, zero cross-regime. XGBoost, Random Forest, and a Transformer all reach in-regime R² of 0.38–0.92 but negative R² on every regime transition.
- In-regime accuracy is uninformative about cross-regime robustness. RF and XGBoost tie in-regime yet RF is strictly worse out-of-regime on every experiment — conventional validation cannot tell them apart.
- Failure is directionally asymmetric. Downward extrapolation (crisis→calm) is catastrophic (R² −2.6 to −27.2); upward is bounded (−0.67 to −1.15). This replicates across three model
Description
Cross-Regime Robustness of Volatility Forecasting: Why a Two-Parameter Mean-Reversion Anchor Generalizes Where XGBoost, Random Forests, and Transformers Fail
Related repositories
Similar projects matched by category, topics, and programming language.
gavamedia
Featured
deltafin
Deltafin is a research project that runs the 2.8-trillion-parameter Mixture-of-Experts model Kimi K3 on a single Apple Silicon Mac (e.g., M1 Max with 64 GB) at about 16 seconds per token, using exact, reproducible inference with local or streaming expert loading.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.