New release — February 2026

Algorithmic Trading with
VectorBT

The complete Python guide to backtesting, optimization, and portfolio management in VectorBT — paired with 88 production-ready strategy files you can run today.

1 Complete Book (PDF)
88 Python Strategy Files
6 Strategy Categories
📖
Included
Algorithmic Trading with VectorBT
⚙️
Included
88 VectorBT Strategy Files
1
In-Depth Book (PDF)
88
Python Strategy Files
6
Strategy Categories
€75
One-Time · Yours Forever

The Book:
Theory That Becomes Working Code

Algorithmic Trading with VectorBT book cover
Included

7 Chapters — What you'll learn

Each chapter maps directly to a working notebook in the code pack.

01
Downloading Market Data
OHLCV, vbt.YFData, timestamps, resampling, NaN handling
02
From Signals to Trades
vbt.Portfolio.from_signals, costs, drawdowns, trade records
03
Parameter Search (Optimization)
Grid search, run_combs, heatmaps, avoiding overfitting
04
Backtesting Strategies
Interactive DMAC dashboard vs random and buy-and-hold baselines
05
Walk-Forward Optimization
Rolling train/test splits, in-sample vs out-of-sample Sharpe
06
Portfolio Optimization
Random search + PyPortfolioOpt, rolling rebalancing every 30 days
07
Portfolio Allocation & Risk Management
Equal-dollar vs volatility-targeted sizing

The Code Pack:
88 Strategies. Zero Filler.

Every file is a complete, runnable Python script. Load your data, set your parameters, run. No babysitting required.

REGIME

Hurst Exponent EMA Cross

Filters trending vs mean-reverting regimes via Hurst exponent; activates EMA crossover signals only in trending conditions.

REGIME

HMM Regime SL/TP

Hidden Markov Model classifies market state and dynamically adjusts stop-loss and take-profit targets per regime.

REGIME

GMM Regime Adaptive

Gaussian Mixture Model identifies volatility regimes and adapts position sizing and signal thresholds to each state.

ML

Decision Tree EMA

Scikit-learn decision tree classifies market conditions and gates EMA trend signals with trained predictions.

ML

Isolation Forest Anomaly

Detects unusual price action and market anomalies using unsupervised isolation forest — avoids noise spike entries.

TREND

Guppy MMA + Pullback

Full Guppy Multiple Moving Average system with pullback entry timing and structured exit logic.

TREND

Triple EMA Crossover

Three-MA system using fast/medium/slow crossover confirmation to filter false breakouts in trending markets.

TREND

ADX Trend Filter

ADX gates EMA crossover signals — only enters when trend strength exceeds threshold, reducing whipsaw losses.

MEAN REV

Bollinger RSI Filter

Bollinger Band mean-reversion gated by RSI extremes — long on lower band oversold, short on upper band overbought.

MEAN REV

Quantile Regression SL/TP

Quantile regression channels define dynamic mean-reversion zones with adaptive stop-loss and take-profit levels.

VOLATILITY

Adaptive Fourier Cycle

Fourier transform identifies dominant market cycles and adapts signal periods dynamically to the current frequency regime.

VOLATILITY

Hilbert RSI

Hilbert Transform extracts instantaneous phase of the market cycle; RSI entries are synchronized to the dominant cycle.

6 Categories:
Every Edge Covered

📊

Regime Detection

HMM, GMM, Hurst exponent, dual-regime, and BBands regime-adaptive strategies.

12+ strategies
🤖

Machine Learning

Decision tree EMA, isolation forest, and IVM BTC regime classification systems.

6+ strategies
📈

Trend Following

EMA crosses, ADX filters, Guppy MMA pullback, DEMA, TRIX, triple EMA, MA ribbon.

20+ strategies
↩️

Mean Reversion

Bollinger RSI, quantile regression channels, enhanced BB, RSI MR with ADX filters.

14+ strategies
🌊

Volatility & Cycles

Adaptive Fourier, Hilbert RSI, ATR breakouts, vol clustering, vol cooling gridsearch.

10+ strategies
🗂️

Optimization & Portfolio

Walk-forward notebooks, grid search, equal/dynamic allocation, ensemble weights.

10+ notebooks

What Traders Say

★★★★★

"The regime detection strategies alone are worth 10x the price. The HMM + GMM implementations saved me weeks of research. Immediately plugged into my live bot."

M
Marcus T.
Crypto Quant, London
★★★★★

"The book explains the 'why' and the code pack gives you the 'how'. I got more from this in a weekend than 6 months building my own VBT strategies from scratch."

S
Sarah K.
Algo Trader, Netherlands
★★★★★

"Clean, well-structured code that actually runs. The walk-forward optimization notebook alone justified the purchase. Already running 8 of these in my portfolio framework."

D
David R.
Quant Researcher, Singapore
Complete Bundle — Book + Code Pack

Everything. One Price.
Yours Forever.

No subscription. No upsells. Instant download the moment you pay.

📖 Algorithmic Trading with VectorBT
⚙️ 88 Strategy Files
One-Time Price
€75
One-time payment
Lifetime access
Algorithmic Trading with VectorBT (PDF) Full Book
All 88 Python strategy files (.py + .ipynb) 88 files
Walk-forward optimization notebooks 12 notebooks
Regime detection suite (HMM, GMM, Hurst) 12 strats
ML-augmented strategies 6 strats
Future updates included
Commercial use license

Secure Stripe checkout  ·  Instant delivery  · 

Common Questions

All strategies are built on open-source VectorBT and work without a Pro license. They're fully compatible with VectorBT Pro too — you'll just get additional performance features on top.
Most strategies use yfinance for daily data or CCXT/Binance for crypto OHLCV. Any pandas DataFrame with standard OHLCV columns works — swapping data sources is typically just changing a few lines in the data loading section.
Intermediate Python and basic quant finance knowledge is recommended. You should be comfortable with pandas and numpy, and understand concepts like backtesting, Sharpe ratio, and drawdown. ML strategies additionally require familiarity with scikit-learn.
These are backtesting and research frameworks built on VectorBT. The signal logic is clean and modular — it's straightforward to extract signals into live systems (Freqtrade, CCXT bots, etc.) but the files are designed for research and optimization workflows.
The book is a PDF. The strategy files are a .zip archive containing all Python (.py) files and Jupyter notebooks (.ipynb). You'll receive download links immediately after payment via email.