RevDog AI

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.

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.

Daily Market State

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.