volarixs

volarixs - applied AI & ML to finance

Explore our latest posts on machine learning, market dynamics, strategy architecture and design

Feature Engineering
Jun 2, 2026

Shrinking the Feature Space: PCA & Autoencoders

Many features are redundant or noisy. High dimensionality = harder to generalize.

PCA
Autoencoders
Features
9 min read
Strategy
May 24, 2026

How Asset Managers Can Implement AI & Machine Learning

Part 2: Infrastructure, Governance & Roadmap. What it takes to implement AI in asset management.

AI Implementation
Governance
Roadmap
18 min read
Deep Learning
May 20, 2026

Neural Networks for Market Data: MLPs, CNNs & LSTMs

We are selective with deep learning. Expensive to train, easy to overfit, harder to debug.

Neural Networks
MLP
LSTM
12 min read
Research
May 14, 2026

Signal Half-Life and Decay: How Long Do ML Edges Really Last?

If you discover a signal today, how long will it work?

Signal Decay
Half-Life
Edge Persistence
13 min read
Strategy
May 7, 2026

How Asset Managers Can Use AI & Machine Learning in Investment Decisions

Part 1: Use Cases & Value. Real-world use cases: idea generation, regime analysis, risk management.

Asset Management
AI & ML
Use Cases
15 min read
Volatility
Apr 27, 2026

Modeling Market Turbulence: GARCH, EGARCH & HAR

Volatility ≠ returns: heavy tails, clustering, mean reversion. Dedicated volatility models are essential.

GARCH
EGARCH
HAR
10 min read
Time Series
Apr 9, 2026

ARIMA, SARIMAX & VAR: When Classical Time-Series Still Win

Explicitly model temporal dependence with transparent structure.

ARIMA
SARIMAX
VAR
9 min read
Benchmarks
Mar 31, 2026

Volatility Forecasting Benchmarks: GARCH, HAR, and ML

Compare GARCH, HAR, and ML models for volatility forecasting.

Volatility
GARCH
HAR
11 min read
Machine Learning
Mar 24, 2026

How Market Regimes Break ML Models

Financial machine learning rarely fails because the model is 'bad'. It fails because the market regime changed.

Regimes
ML
Backtesting
8 min read
Models
Mar 17, 2026

Boosted Trees for Alpha: XGBoost & LightGBM

Gradient boosting dominates tabular ML. Learn how XGBoost and LightGBM deliver strong performance.

XGBoost
LightGBM
Boosting
11 min read
Features
Mar 10, 2026

The 19 Most Important Features for Equity Return Forecasting

Most ML performance in finance doesn't come from the model — it comes from the features.

Features
Alpha
Equities
12 min read
Methodology
Feb 27, 2026

Rolling Windows for Financial ML: A Complete Guide

If you use financial data and your model does not use a rolling window, the backtest is wrong.

Rolling Windows
Time Series
Backtesting
10 min read
Evaluation
Feb 16, 2026

Beyond Sharpe: A Research Framework for Evaluating ML Trading Strategies

Sharpe ratio is dangerously incomplete for ML strategies.

Evaluation
Metrics
Sharpe
15 min read
Models
Jan 28, 2026

Random Forests in Finance: Nonlinear Signals Without the Drama

Tree-based ensembles capture nonlinearities and interactions in market data.

Random Forest
Extra Trees
Trees
10 min read
Models
Jan 5, 2026

From Linear Regression to Lasso: Fast, Interpretable Baselines

Linear and regularized regressions still do serious work in finance.

Linear Regression
Ridge
Lasso
12 min read
Regimes
Dec 12, 2025

Market Regimes, Clusters & HMMs: Teaching Models to Respect the Environment

Episodes where statistical properties are stable enough: high vol vs low vol, risk-on vs risk-off.

K-Means
GMM
HMM
11 min read
Architecture
Nov 23, 2025

Building a Universe-Wide Prediction Grid

An alpha factory needs predictions for every asset at multiple horizons from multiple models.

Prediction Grid
Scaling
Alpha Factory
14 min read
Evaluation
Oct 8, 2025

Regime-Conditioned Performance: Measuring ML Robustness

Most backtests report a single Sharpe. But ML models fail by regime.

Regimes
Robustness
Performance
12 min read
Volatility
April 27, 2026
10 min read

Modeling Market Turbulence: GARCH, EGARCH & HAR for Volatility Forecasting

Volatility ≠ returns: heavy tails, clustering, mean reversion. Dedicated volatility models are essential for risk management, position sizing, and VaR.

1. Why Dedicated Volatility Models

You can forecast returns with a generic regressor, but volatility refuses to behave like one. Returns are close to unpredictable day to day; their magnitude is not. That asymmetry is why volatility gets its own family of models — they are built around the few properties that show up in almost every asset:

  • Heavy tails: extreme moves happen far more often than a normal distribution predicts
  • Clustering: calm follows calm and turbulence follows turbulence — high-vol days arrive in runs, not isolation
  • Mean reversion: once a shock fades, volatility drifts back toward its long-run average

Get the vol forecast wrong and everything downstream inherits the error: risk limits, position sizing, and VaR all rest on it. That payoff is what justifies a dedicated model rather than a generic one.

Volatility Clustering Visual

2. GARCH Family

Intuition: today's volatility depends on yesterday's shock and yesterday's volatility.

GARCH(1,1):
r_t = σ_t ε_t, ε_t ~ N(0,1)
σ_t² = ω + α r_{t-1}² + β σ_{t-1}²
where ω > 0, α ≥ 0, β ≥ 0, and α + β < 1 for stationarity

EGARCH / GJR-GARCH: allow for asymmetry (downside shocks impact vol more).

EGARCH(1,1):
log(σ_t²) = ω + α(|ε_{t-1}| - E|ε_{t-1}|) + γε_{t-1} + β log(σ_{t-1}²)
The γ term captures asymmetry: negative shocks (γ < 0) increase volatility more than positive shocks

GARCH Response to Shock

Note how the large shock raises volatility and then gradually mean reverts. This demonstrates the clustering property of volatility: high vol periods follow high vol periods.

3. HAR-RV

Heterogeneous AutoRegressive model for realized volatility. Uses lags at multiple horizons: 1-day, 5-day, 22-day, etc.

Intuition: traders with different time horizons contribute to volatility dynamics.

4. How This Maps to volarixs

Volatility is one of the model classes you can select when you set up an experiment — alongside regression, tree & boosted, neural networks, and time-series models. So a volatility forecast in volarixs is built the same way as any other model: pick datasets and a feature set, choose a target horizon, and run it walk-forward over a time window, with results tracked per run.

A volatility forecast is rarely the end of the story, though — it is an input to other decisions. The pieces that consume it are what volarixs is built around:

  • risk-adjusted signals, where a vol estimate scales raw direction and confidence
  • macro and regime context, which records the inflation, policy, and liquidity state each run was made under
  • the Factory, where production models are trained, monitored, and turned into predictions
GARCH
EGARCH
HAR-RV

Get new research in your inbox

Applied AI & ML for the buy-side — new research on signals, regimes, and strategy design, straight to your inbox. No noise.

Ready to forecast volatility?

Build volatility models in volarixs.

Explore More Research