Research
Data-driven research validating our cryptocurrency rating system and grid trading methodology. All studies use blind forward testing to ensure realistic performance expectations.
Featured Research
ETS Weight Optimization: 938 Combinations Tested
Finding the Optimal ADX / Entropy / Hurst / dH/dt Balance for Grid Trading Signals
Data-driven optimization of ETS Trend Strength Indicator weights against 39 known grid trading outcomes. Key finding: ADX is 60% of the signal (was 35%). Hurst derivative (dH/dt) at 10% is 2× more predictive than Hurst level (5%). Composite prediction score improved by 74%.
Can We Predict When the Market Changes?
Testing Regime Transition Detection for Smarter Grid Trading
Tests 6 spacing strategies including Hurst derivative, composite transition score, and Hidden Markov Models across 3 rolling windows. Key finding: static 2.59% wins 51% of the time, but ETS Current (already in CoinRoc) is the second-best approach at 31%. Hurst derivative shows promise for catching transitions the current indicators miss.
All Research Papers
February 2026
ETS Weight Optimization: 938 Combinations Tested
Finding the Optimal ADX / Entropy / Hurst / dH/dt Balance for Grid Trading Signals
Can We Predict When the Market Changes?
Testing Regime Transition Detection for Smarter Grid Trading
Can AI Pattern Recognition Improve Grid Trading?
Testing Hopfield Neural Networks — Nobel Prize Physics Meets Crypto Markets
Adaptive Grid v2.1: Does Volatility-Adjusted Spacing Work?
Testing ATR-Based Grid Spacing Against the Proven Static 2.59% Baseline
Three Layers to Better Crypto Returns
How Rating Selection, Portfolio Optimization, and Dynamic Grid Trading Each Independently Improve Performance
Rolling Backtest Validation Study
Can You Trust These Returns? A Plain-Language Validation of Our Grid Trading Methodology
HRP vs MVO Portfolio Construction
Comparing Hierarchical Risk Parity Against Mean-Variance Optimization
Grid Trading Profitability Across Exchanges
Why Exchange Choice Matters More Than Crypto Selection
Rating System Effectiveness Study
How Multi-Factor Ratings Improve Grid Trading Returns by 37-66%
* Note on this figure, added 2026-08-05: The 0.886 correlation (and the return/win-rate figures on this page) were measured under an earlier version of the rating formula (dated 2026-01-29). The formula has since been re-optimized three times; internal walk-forward testing as of 2026-05-13 indicates a higher correlation under the current formula. We are re-running this study under the live formula and will republish updated figures. The qualitative finding — that higher-rated assets have historically outperformed lower-rated ones — is not affected by this note; the exact numbers above should not be cited as describing today's system until the re-run is complete.
See the Rating System in Action
Explore our Discovery page to see real-time ratings for 80+ cryptocurrencies, or read our articles for practical trading insights.
Our Research Methodology
All CoinRoc research uses blind forward testing: Year 1 data calculates parameters, Year 2 data measures performance. We also employ rolling forward tests with 19 independent windows for statistical validation. We believe in transparency and publish our methodology for peer review.