Comprehensive analysis of Coppock-based technical signals, including: (1) multi-timeframe Coppock strategy design, (2) security-level Coppock scores using voting logic, (3) performance comparison across multiple Coppock variants, and (4) risk/return profiling of the final strategy.
Perceptron Intelligence – Research Portal
Research reports for Genus Capital Management — Confidential
Confidential. Contact: Pavan Mirla, office@perceptron.solutions
🔬 Research & Analysis Tools
[Breakout Analysis Chart]
Technical Analysis
-
Breakout analysis tool. Coppock Scatterplots
Tool: Breakout analysis tool.
[Fama French Factors Chart]
Fama French Factor Research
-
Fama French Factors and Model Portfolios
Research Tool: generated weekly/monthly (pdf form). This helps you see: When value beat growth (HML - Value vs Growth), When small caps outperformed large (SMB - Small vs Large cap return), When profitability mattered (RMW - Profitable vs Unprofitable), How yield curve shape predicted recessions. Sources: Kenneth R. French Data Library (Fama-French factors), FRED (Federal Reserve Economic Data) (US Treasury yields).
[Coppock Curve Chart]
Technical Analysis with Coppock Curve
-
Coppock signal measures momentum over 11 and 14 months
Tool: Coppock signal measures momentum over 11 and 14 months (hence “11-14-10” in title — 10 = smoothing period). Change the ticker as required.
[Rotation Analysis Report]
Rotation Analysis
-
Weekly Pdf report
Tool: Weekly Pdf report. Proprietary algorithm.
[Platform Index Analysis Chart]
Platform Index Analysis
-
Platform Index Analysis Tool
Tool: This tool performs a Principal Component Analysis (PCA) on the daily returns of platform indices, derived from selected platform identification and their underlying stocks.
[Sector Signal Dashboard]
Multi-Indicator Technical & ML-Driven Sector Forecasting
-
Sector-Wide Signal Engine
Integrates Sector data with US_REBALANCE benchmark to perform multi-indicator technical analysis, feature importance ranking, and ML-driven forecasting. Trains categorical (classification) and regression models to identify drivers of sector returns, generates forward return predictions, and backtests a strategy based on consecutive positive signals. Outputs include cumulative returns, performance metrics, and a PDF research report.
[PCA Factor Dashboard]
Macro/BARRA Factors & PC Portfolios
-
Cross-Sectional PCA Factor Dashboard
Reads monthly factor/return panels (BPMandReturns_1998to2024) plus gvkey→company map, cleans/z-scores macro and TP_* BARRA-style factors, fits PCA (default 5 PCs), joins scores back to data, and runs date-wise cross-sectional regressions of excess returns (size/liquidity adjusted) on PCs. Builds PC-sorted decile portfolios (default PC1), computes cumulative long-short and relative returns, annualized perf/IR, IR heatmap, and saves plots/tables/CSVs (loadings, variance, metrics, top PC1 names) into output/pca_report.pdf.
📑 Research Reports
2025-Q2/Q3
2025-Q1
Research comparing rule-based and machine learning approaches for sector trend prediction. Evaluates multiple ML models on technical signals and benchmarks them against a non-ML baseline: a vote-based trade signal using Coppock scores.
2024-Q4
Integrated framework for macro regime detection and sector rotation. Combines: (1) ML-based market regime identification, (2) NLP-driven sentiment analysis of news/social media, and (3) unsupervised clustering (k-means, t-SNE) of sector returns to reveal cyclical/defensive, growth/value, and commodity/service dynamics. Builds on Q3 2024 work with heatmap visualizations and cumulative trend analysis for tactical allocation.
2024-Q3
Foundational research on macro regime detection using HMM and SHAP-interpretable ML models. Focuses on predicting ETF (sector proxy) returns under varying economic conditions. Integrates NLP for financial text and sentiment analysis, with SHAP values used to explain feature contributions—grounded in cooperative game theory (Shapley, 1953)—to enhance model transparency and strategic decision-making in asset management.
2024-Q2
Extension of the vote-count portfolio framework using dynamic signal weighting. Evaluates multiple time series transformations—including Monthly Difference, Rolling Mean (various windows), Exponentially Weighted Moving Average (EWMA), and Expanding Mean—to denoise signals, capture momentum, and adapt vote weights over time for improved portfolio responsiveness and risk-adjusted returns.
2024-Q1
Introduces a weighted PCA methodology to derive orthogonal risk factors and forecast asset returns. Portfolios are ranked by weighted PCA scores and grouped into deciles (0–9), with Decile 0 delivering the highest cumulative returns. The approach aligns with Arbitrage Pricing Theory (APT), treating principal components as priced risk factors. Investors implicitly bet on the persistence of associated risk premiums through this construction.
2023-Q4
Deep dive into the Vote Count methodology across 500+ factor combinations (span, transformation, cutoff). Monthly portfolios are evaluated for excess returns, information ratio, and hit rate. Includes correlation analysis of raw factor values to identify and prune redundant signals—enabling a leaner, more robust set of inputs for portfolio construction while preserving predictive diversity.
2023-Q2
Early integration of Vote Count methodology with ML-driven factor analysis. Uses rolling-window correlations (e.g., yield curve vs. factors) for regime detection, multivariate sequence prediction over 5-year windows, and ML-based feature importance to score factors. Portfolios are formed by vote thresholds (e.g., ≥3 votes), with backtests showing strong outperformance and high information ratios for high-vote portfolios versus low-vote counterparts.
2023-Q2
Analysis of factor return distributions with focus on kurtosis as a measure of tail risk. Key findings: (1) normalized momentum factors align with BARRA distribution profiles, (2) growth factors exhibit elevated kurtosis, and (3) kurtosis diminishes when using moving averages longer than 24 months. Includes active return reporting for quantile and cutoff portfolios using winsorization protocols established in February 2023.
2023-Q1
Foundational study comparing quantile-based vs. absolute cutoff-based portfolio construction. Evaluates impact of kurtosis, skew, and average factor exposure on returns across overlapping and non-overlapping buckets. Determines optimal tile size (decile vs. quintile) and validates cutoff ranges for robust cross-sectional ranking—establishing core methodology later used in Vote Count and factor scoring frameworks.
2023-Q1
Extension of Q4 2022 cutoff methodology using moving average-transformed factor exposures. Compares two winsorization approaches (fixed ±3 vs. percentile-based renormalization) and evaluates octile portfolios via information ratio against benchmark. Establishes a robust, long-only ranking pipeline for cross-sectional factor investing.
2022-Q4
Foundational analysis comparing quantile and cutoff portfolios under various moving average transformations of factor exposures. Evaluates performance across tenure-based MA windows to identify robust signal preprocessing methods for long-only cross-sectional strategies. Establishes the baseline methodology later extended in 2023 Q1–Q2 research.
2022-Q4
Evaluation of dynamic long-only portfolios using transformed BARRA fundamental factor exposures. Applies moving averages (3M–60M) and moving differences to raw factor data, followed by monthly rebalancing based on transformed scores. Analyzed in xBSL space to assess responsiveness to market regime shifts.
2022-Q3
Development of a dual-path factor scoring framework: (1) risk premium approach using cross-sectional regressions of BARRA exposures vs. excess BSL returns, smoothed via moving averages; and (2) direct moving average transformation of factor exposures with grid-search optimization of lookback windows. Evaluated over April–August 2022, forming the basis for dynamic portfolio construction.
2022-Q2
Hybrid methodology combining PCA-based dimensionality reduction on tagged BARRA factor subgroups (top 3 eigencomponents per group) with monthly cross-sectional regressions against 3-month forward excess BSL returns to estimate dynamic risk premiums. Derived eigen-variables serve as inputs for portfolio scoring and construction, establishing an early framework for factor synthesis and signal generation.
🗓️ Meeting Notes & Strategic Insights
- Run PCA on ex-industry returns instead of active returns.
- Explore theme detection model based on EWS signals.
- Update principal components: rank PC1 tickers by stocks.
- Use rolling PCA windows instead of a single full-period PCA across longitudinal data.
- Proposed 3x3 matrix for Coppock cutoff periods (weekly/monthly/daily).
- Design tree-structured state model using individual (non-aggregated) Coppock scores.
- Bucket securities into tree nodes based on W/D/M Coppock directions.
- Visualize weekly Coppock vs. aggregate Coppock overlay.
- Add MA50/MA200 crossovers: “Dark Cross” (bearish), “Golden Cross” (MA40 > MA200).
- Prioritize Monthly Coppock for strategic signals.
- Plan: display latest weekly Coppock prediction per industry group.
- Next step: build unified Regime Detection Dashboard.
- Analyzed hit ratio across all 24 sector time series.
- Resolved duplication issue: sector/index series were incorrectly mapped.
- Defined Buy/Hold/Sell logic: long high-vote, short low-vote sectors.
- Confirmed portfolio construction: treat all 24 sectors as individual tradable units (not a single composite).
- Agreed to maintain both aggregate and sector-by-sector views.
- Finalized forecasting setup: 5-year feature window → predict t+3 (weekly), validate over 4+ weeks forward.