Why a Random Forest Beats a Genius: Ensemble Methods for Indian Equities
A working note from RevDog.ai — applying Chapter 6 of López de Prado's Advances in Financial Machine Learning to the NIFTY 500 ML pipeline, with reproducible experiments.
Latest
What's the Right Answer? Labeling and Sample Weights for Indian Equities
Before a model can learn anything, you have to tell it what "right" looks like. That's labeling, and it's the step quants are sloppiest about — usually a one-liner: y = sign(return over next N days). This post is about why that one-liner quietly corrupts
Your Model Has Amnesia: Fractional Differentiation for Indian Equities
A working note from RevDog.ai — applying Chapter 5 of López de Prado's Advances in Financial Machine Learning to NIFTY indices and stocks, with real Zerodha Kite data.
The Hidden Lie In Every Minute Bar: Why Dollar Bars Matter For Indian Equity Quants
A working note from RevDog.ai — building a dollar-bar pipeline for NIFTY 500 cash equities, inspired by López de Prado's Advances in Financial Machine Learning.
NIFTY SmallCap 250: Stress Compression — sharp drop with low dispersion
Cut smallcap exposure to 55–60%, add to IT on weakness, and keep 50% in quality defensives until breadth improves.
Everyone Says "Buy Low, Sell High." Nobody Says How Low Is Low Enough.
Everyone says buy the dip. Nobody says where. A 5-layer framework to find the exact price to place your bid — and when to wait.
When Treasury Yields Turn, Wars Wind Down: Reading the Signal Behind the Headlines
I looked at 807 days of US bond market data and found that when borrowing costs cross a threshold, they always come back down — and policy reversals follow. When elevated yields start falling, Indian stock markets averaged 3x their normal returns over the next 20 days.
Triangle Strategy: Near-Zero Correlation Gave Me 50% More Return with 12% Less Risk
I screened 112 Indian stocks across 247 trading days, found zero negative correlations — so I crossed the border into AI. One stock gave me -0.02 correlation, +22% backtested return, and nearly doubled my risk-adjusted ratio. Full framework inside.
NSE Down 15%. Bonuses Are In. So I Built a Barbell Portfolio.
This isn't an investment advice — it's a framework. 112 stocks screened, 247 trading days analyzed, and the two-stock approach I landed on.
Why We Stopped Building a Strategy and Started Building an Engine
How a small-cap quant system evolved from a single backtest into a configurable factor platform — and why that distinction matters for Indian portfolio managers.
Observe-Reason-Act-Converge: A Design Pattern to Build an AI Data Engineer Agent
A design pattern for AI agents that monitor, diagnose, and fix data pipelines autonomously — so your data team can focus on building, not babysitting cron jobs.
We Tested Whether More Diversification Helps a Mean-Reversion Strategy. It Doesn't.
We tested 5 position-sizing configs for our NSE SmallCap mean-reversion strategy — from 5 to 15 concurrent positions. More diversification hurt every metric. The 7-position limit acts as a quality filter, not a risk concentration.
We Extended Our Walk-Forward Window from 6 to 15 Months. Here's What We Found.
We extended our walk-forward factor validation from 6 to 15 months on NSE SmallCap 250. Signal got stronger — IC improved, stability increased, and two new persistent factors emerged that a shorter window couldn't detect.
SmallCap Dislocation: Why This Mean-Reversion Edge Survived 18 Attempts to Break It
Most mean-reversion strategies break when you touch the parameters. This one didn’t. After 18 sensitivity tests, removing logic, and tightening constraints, SmallCap Dislocation held up—because it’s driven by forced selling, not curve-fitting.
SmallCap Dislocations: A Quantitative Alpha Source Most NSE Small-Cap Funds Ignore
Indian small caps misprice during forced selling, not fundamentals. Using a day-by-day portfolio simulation, we tested a dislocation strategy that exploits liquidity shocks—64.8% win rate, −1.02 skew, and 3.1% max drawdown with strict risk controls.
Mean Reversion vs Trend Following in NSE Small-Caps: The Return Distribution Most Traders Ignore
Most NSE small-cap traders obsess over indicators. That’s a mistake. The real difference between mean reversion and trend following isn’t RSI or breakouts—it’s the return distribution you’re betting your capital and psychology on.
Exit Criteria That Actually Work in Small-Caps
We tested multiple exit models in a small-cap strategy and found that binary exits destroy value. A score-driven decay framework with hysteresis improved returns by 7.4pp, raised Sharpe, and cut turnover by 46%.
Low IC, High Sharpe: The Quant Paradox Most Factor Models Get Wrong
Most quants chase high IC factors. That’s a mistake. This article breaks down, with real numbers, how low-IC quality signals can outperform through volatility suppression, regime behavior, and correct portfolio construction.
Why We Didn’t Go Aggressive in a “Risk-On” Small-Cap Market: An Empirical Test of Portfolio Concentration
Should risk-on markets mean aggressive concentration? We tested 8–10 stock portfolios across regimes using live and backtested data. The result surprised us: concentration destroyed Sharpe. Here’s what the data actually says.
When Intuition Fails: A Data-Backed Look at 200DMA Extremes
We tested a common belief: avoid stocks far above their 200DMA. The data showed the opposite—momentum persisted. More importantly, stocks 20%+ below their 200DMA delivered 2–4× higher monthly returns in extreme regimes. That non-linear insight reshaped our model.
Decision Traces: Why Systematic Investing Needs to Explain Why, Not Just What
Most investment systems record outputs, not reasoning. Decision traces capture why a system acted at the moment of commitment—inputs used, constraints applied, actions taken—turning opaque models into legible, self-auditing decision engines.
Backtests and Walk-Forward Validation Answer Different Questions — and Confusing Them Is Costly
Backtests and walk-forward validation serve different purposes. One measures historical outcomes; the other tests whether signals actually persist out-of-sample. Robust systems require both—used correctly and in the right order.
When Factors Stop Working: How Regime-Aware Models Reduce Drawdowns in Indian Equities
Most factor models fail not because signals disappear, but because they are trusted for too long. This note explains how regime-aware factor gating, conditional growth, and governance caps were implemented in RevDog V3 to manage drawdowns in Indian equities.
When “Fair” Isn’t Necessary: Why RevDog Moved Away from Sector-Relative Scoring
RevDog tested sector-relative vs absolute scoring in its V2→V3 transition. With a 0.95+ rank correlation across 111 stocks, results showed normalization mattered far less than regime-aware factor gating—leading to a simpler, more robust V3 design.