The Method

The Q/V/M Framework

Every stock in our universe receives three independent scores, each on a 0–100 scale. These map to the three dimensions that academic research and practitioner experience have shown to drive long-term returns:

Each pillar is built from multiple underlying factors, weighted by the strength of the evidence behind them. The factors are all listed below; the precise weights are our secret sauce. You can see every stock's pillar scores and factor-level breakdown on its own page in Ranked Stocks, or filter on them directly in the Screener.

Quality Factors

Quality captures franchise strength and financial health in three groups. Franchise metrics carry the most weight: a durable moat matters more than any single balance-sheet ratio.

Franchise Quality

Return on Invested Capital, Return on Equity, Gross Profit to Assets (Novy-Marx's profitability factor), operating margin, and Free Cash Flow to Assets. High, stable returns on capital signal a durable moat; the cash-flow checks catch profits that exist only on paper.

Piotroski F-Score

A year-over-year checklist covering profitability, cash-flow quality, leverage change, and operating efficiency. Improving fundamentals score; deteriorating ones don't.

Balance-Sheet Safety

Debt-to-equity, current ratio, and interest coverage. Lower leverage and comfortable debt service mean less fragility in downturns.

Two fairness rules keep these ratios honest. First, profitability metrics are measured on trailing-twelve-month data wherever four clean quarters exist, so a company mid-turnaround is scored on where it is now, not on a fiscal year that ended twelve months ago. Second, companies whose book equity has gone negative purely through years of buybacks (a shareholder-friendly behaviour, not distress) are scored neutrally on the equity ratios rather than penalised for a mathematically undefined number.

Value Factors

Value compares market price to fundamental anchors. We use six trailing ratios, never forward estimates, so no single metric's blind spot dominates:

Price-to-Earnings

The classic multiple, on trailing twelve-month earnings, compared within each sector.

EV/EBITDA

Enterprise value over operating earnings normalises for capital-structure differences, so a leveraged business can't look artificially cheap.

Price-to-Free-Cash-Flow

Rewards companies generating real cash, not just accounting profits. The hardest ratio to manipulate.

Price-to-Book

The Fama-French anchor, most informative for asset-heavy sectors.

Dividend Yield

Computed from dividends actually paid over the trailing twelve months: a tangible return that also signals management confidence in cash flows.

Price-to-Sales

Useful for cyclical or early-stage businesses where earnings are volatile.

Momentum Factors

Momentum captures the market's own signal. Price trend sets the tone; earnings trend confirms it:

Price Momentum

Proximity to the 52-week high (George & Hwang's strongest single price signal), 6-month relative strength versus the benchmark, and the 50-day/200-day moving-average ratio as trend confirmation. We deliberately exclude the most recent-month window, which sits in short-term reversal noise.

Earnings Momentum

Analyst EPS revisions over the last 4 and 12 weeks, the spread between forward and trailing EPS, and quarterly earnings growth. Upward revisions are one of the best-documented leading indicators of further gains.

How Scoring Works

Raw fundamentals are transformed into comparable scores through a multi-step process designed to be fair across sectors, current rather than stale, and robust to missing data.

Trailing-Twelve-Month Basis

Profitability, cash-flow, and valuation inputs are measured on the trailing twelve months wherever a clean TTM can be assembled from quarterly filings; balance-sheet items use the most recent quarter. Annual-report-based screeners can lag reality by a year on fast-moving businesses.

Sector-Relative Percentiles

Every metric is ranked within its sector, so a cheap utility doesn’t automatically beat an expensive tech stock. Apples are compared to apples.

Thin-Sector Blending

Sectors with fewer than 20 stocks get a weighted blend of sector and universe percentiles, preventing small-sample distortions.

Missing Data Penalty

Missing values receive a score of 25 (below median) rather than being ignored. No free passes for incomplete filings.

StockRank Re-Percentiling

The final score is the re-percentiled average of Quality + Value + Momentum. Re-percentiling spreads scores across the full 0–100 range, counteracting the Central Limit Theorem’s tendency to bunch averaged percentiles toward 50.

StockRank: The Composite Score

The three pillar scores are combined into a single StockRank from 0 to 100: a percentile against the whole universe, so a StockRank of 90 means the stock scores better than 90% of everything we cover.

We don't ask you to take the ranking on faith. Every month we snapshot the universe into score deciles and track how each decile actually performs afterwards; if the model works, higher deciles should beat lower ones. A public Decile Tracker is in preparation and goes live once the current round of scoring refinements settles.

Insider & Buyback Signals

Alongside the quantitative score, we collect regulatory filings for director dealings, substantial-shareholder moves, and company share buybacks in 28 of our 30 markets, from SEC Form 4s and UK PDMR notices to Japan's 5%-rule reports and Hong Kong's disclosure register. Insiders buying with their own money, and companies retiring their own shares, are two of the most credible outside confirmations a thesis can get.

These signals appear as Director Trades and Buybacks tiles on every covered stock page, feed the screener's insider columns, and stream into the consolidated global insider feed.

AI Conviction Layer

Quantitative scores alone can miss breaking news: fraud allegations, regulatory action, or transformational deals. Our AI news filter adds a qualitative overlay.

For every stock that passes the quantitative screen, Google Gemini analyses recent news from DuckDuckGo, Finviz, SEC EDGAR, and NewsAPI. Each stock receives one of three verdicts:

Stocks with missing AI verdicts default to FLAG as a safety measure: nothing gets a clean bill of health it hasn't earned. The highest-conviction names surface as AI Champions.

Macro Regime Detection

Stock picking doesn't happen in a vacuum. Four macro indicators are combined into a composite regime signal that frames how aggressively the model leans into its picks:

VIX

Implied volatility index. Elevated VIX signals market stress.

Yield Curve

10Y minus 2Y Treasury spread. Inversion has historically preceded recessions.

Credit Spreads

Investment-grade corporate bond spreads over Treasuries. Widening spreads indicate tightening financial conditions.

Fed Policy

Federal funds rate trajectory and forward guidance tone.

The composite maps to three regimes: RISK_ON, NEUTRAL, and RISK_OFF. The current regime, and the market-by-market health picture behind it, is always live on Market Pulse.

Academic Foundations

Every factor in our scoring system traces back to peer-reviewed research. The table below summarises the key papers and their findings.