Stacking Sats Logo

Stacking Sats is an open source initiative for building, backtesting, and deploying optimal Bitcoin accumulation strategies for both retail and institutional investors.

Quick Links

AboutDocumentation

Connect

DiscordDiscordXX (Twitter)LinkedInLinkedInGitHubGitHub
© 2024 Stacking Sats. All rights reserved.
PrivacyPrivacy Policy•TermsTerms of Service
Stacking Sats
BetaWe're currently optimizing the experience
Stacking Sats Docs
Stacking Sats Docs
IntroductionQuick Start
OverviewSignal InterpretationAccumulation StrategiesAssumptions and Limitations
OverviewWeight ComputationFeature ConstructionSignal CompositionDynamic MultiplierModel Constants
OverviewPerformance ResultsSPD CalculationModel ScoreValidation Checks
OverviewAgent APIAgent builder guideGlossaryBitcoin
OverviewContributing
Backtest

Backtest

Model Score

Explains how the composite model score is calculated and how to interpret it.

Last reviewed
March 10, 2026

The model score combines win rate and exponential-decay percentile into a single benchmark.

As of: 2026-03-08


Source artifact: backtest-metrics.snapshot.json


Generation command: python backtest.py

Score Breakdown

MetricValueFormula
Model Score60.33%0.5 × win_rate + 0.5 × exp_decay_percentile
Mean Excess+4.07%dynamic_percentile - uniform_percentile
Median Excess+4.41%Typical outperformance
Relative Improvement11.44%excess / uniform × 100
Ratio1.11dynamic / uniform

Performance Summary

  • 64.45% win rate (1,646 wins / 908 losses)
  • 11.44% relative improvement on average
  • Recent weighted percentile average: 56.21%

Worked Example

Using a hypothetical win rate of 64.00% and exponential-decay percentile of 56.00%:

model_score = 0.5 * 64.00 + 0.5 * 56.00 = 60.00%

This example is interpretation guidance only. Operational caveats remain in Assumptions and Limitations.

Prerequisites

  • Performance Results
  • Signal Composition

Next Step

Validation Checks

Related Pages

  • Overview
  • SPD Calculation
  • Model Constants
  • Glossary

SPD Calculation

Defines sats-per-dollar (SPD), percentile normalization, and interpretation ranges.

Validation Checks

Lists model validation safeguards used to prevent leakage and calculation errors.

On this page

Score BreakdownPerformance SummaryWorked Example
Stacking Sats Logo

Stacking Sats is an open source initiative for building, backtesting, and deploying optimal Bitcoin accumulation strategies for both retail and institutional investors.

Quick Links

AboutDocumentation

Connect

DiscordDiscordXX (Twitter)LinkedInLinkedInGitHubGitHub
© 2024 Stacking Sats. All rights reserved.
PrivacyPrivacy Policy•TermsTerms of Service