Perceptron Intelligence – Research Portal
Research reports for Genus Capital Management — Confidential
Confidential. Contact: Pavan Mirla, office@perceptron.solutions
🔬 Research & Analysis Tools
| Category | Tool | Description |
|---|---|---|
| Fixed Income / Rates Research | PCA Bond Yields — Yield Curve Factor Analysis | Decomposes the US Treasury yield curve (1M to 30Y) into three principal components: Level (parallel shift), Slope (steepening/flattening), and Curvature (twist). Fetches live FRED data daily. Includes yield curve snapshot vs history, monthly heatmap, PC factor time series, loadings by maturity, explained variance, 10Y-2Y spread vs PC2, and rolling regime volatility. |
| Technical Analysis | Breakout Analysis — Coppock Scatterplots | Cross-sectional scatter tool: plots multiple tickers simultaneously using Coppock momentum scores. Quickly identify which stocks are breaking out or reversing across a peer group. Enter a custom series of tickers to compare their Coppock momentum positions in one view. |
| Technical Analysis with Coppock Curve | Single-Ticker Coppock Analysis — Buy/Sell Signals | Deep-dive tool for any individual ticker: enter a symbol to generate a full Coppock momentum report. Shows cumulative return with annotated buy/sell signals, weekly and monthly Coppock curves overlaid on price, a state heatmap, and a forward-return performance table at 1M, 2M, and 4M horizons. The Coppock curve uses 11 and 14-month ROC inputs with a 10-period WMA smoothing. |
| Rotation Analysis | Sector Rotation Report Gallery | Published RRG-style sector rotation reports — four-quadrant momentum analysis across sectors, indices, or custom tickers. Request a bespoke analysis directly from the gallery. |
| 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. |
| 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. |
| 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). |
| 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
| Period | Report | Type | Link |
|---|---|---|---|
| 2025-Q2/Q3 | Multi-Timeframe Coppock Strategy: Technical Signals Research 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. |
Technical | View Report |
| 2025-Q1 | Classification-Based Technical Trading Strategies Using ML Indicators 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. |
ML Research | View Report |
| 2024-Q4 | Macro Regime Change and Sector Rotation Research 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. |
ML Research | View Report |
| 2024-Q3 | Macro Model Regime Change Analysis 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. |
ML Research | View Report |
| 2024-Q2 | Static and Dynamic Vote Counts: Portfolio Construction with Time Series Transformations 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. |
Technical | View Report |
| 2024-Q1 | Weighted PCA Research Findings: Factor-Based Portfolio Construction 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. |
Quant Research | View Report |
| 2023-Q4 | Vote Count Additional Insights: Factor Performance and Correlation Analysis 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. |
Quant Research | View Report |
| 2023-Q2 | Vote Counts & Machine Learning Applications: Factor Ranking and Regime-Aware Portfolio Construction 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. |
Quant Research | View Report |
| 2023-Q2 | Kurtosis Metrics and Factor Distribution Analysis 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. |
Quant Research | View Report |
| 2023-Q1 | Decile and Quintile Transformation Cutoffs: Portfolio Construction Methodology 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. |
Quant Research | View Report |
| 2023-Q1 | Transformation Cutoffs & Octile Analysis: Long-Only Portfolio Framework 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. |
Quant Research | View Report |
| 2022-Q4 | Long-Only Factor Transformations Review: Moving Averages and Portfolio Construction 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. |
Quant Research | View Report |
| 2022-Q4 | Fundamental Factor Transformations Analysis: Dynamic BARRA-Based Portfolios 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. |
Quant Research | View Report |
| 2022-Q3 | Risk Premiums Analysis and Moving Averages: Factor Scoring Methodology 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. |
Quant Research | View Report |
| 2022-Q2 | PCA and Cross-Sectional Regression Insights: Factor Synthesis and Risk Premium Estimation 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. |
Quant Research | View Report |
🗓️ Meeting Notes & Strategic Insights
Research Portal & Tools Update
- Created dynamic web portal for research documentation (password-protected, all tools server-hosted).
- All tools now run on server vs static PDFs; real-time data pulls from Jacob's shared folder.
- PCA walk-forward: rolling 5-year windows vs expanding; targets: total return, x-beta, x-beta+industry.
- PC4 showing strong performance — long-term reversal, momentum, and profitability factors loading.
- Sector probability forecasts: banks showing high probability up; can automate to biweekly cadence.
- Sector rotation tool: four-quadrant visualisation, real-time updates, custom date ranges.
- Action: verify energy/rates data accuracy with Jacob before production publication.
Technology Strategy & AI Planning
- Firm-wide AI competency initiative across all departments.
- Legacy systems: 35-year-old portfolio accounting (RamKit) — plan to extend via AI augmentation, not full replacement.
- Convert accounting system to API with scripting language interface.
- Pavan: industry research project — survey current investment firm AI tools and data structures; recommendations for 2-year technology roadmap (timeline 1–2 months, informing fiscal 2027 planning).
- Microsoft Copilot evaluation: firm considering ~$30K annual subscription; industry consensus is Copilot underperforming expectations — assess better alternatives before contract signing.
Market Analysis & Alpha Generation
- PCA expansion: include all asset classes (stocks, bonds, commodities, macro data).
- "Grok attempt" — massive transformer model for Russell universe; focus on finding underlying market drivers as hedge funds do.
- Text-based alpha: Fed notes, commentary, tweets as data sources; create custom indices from qualitative information; quantify unstructured data for competitive advantage.
- Macro factor integration identified as critical given current volatility.
Production Improvements
- Sector rotation model verification needed with Jacob — energy and rates showing unexpected directions.
- Technical model summary tables: biweekly publication for all industry groups, integrated into web portal vs email.
- PCA loadings time series: track PC factor loadings over time to identify regime changes (novel approach to market structure evolution).
Next Steps
- Pavan: fix web portal server issues, send bond market PCA research.
- Jacob: add sector data to shared folder for real-time access, verify rotation model calculations.
- Lisa: schedule planning meeting week of Feb 9, continue biweekly meetings before lunch.
- Team: workshop planning incorporating AI strategy direction.
- 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.