MScore

Methodology

Last updated: 2026-03-06

MScore is a multi-factor stock scoring platform. Every stock receives a score from 0 to 100 based on four complementary dimensions: momentum, value, quality, and financial solidity. Think of it as a comprehensive health check for any stock — not a prediction of where it will go, but a data-driven snapshot of where it stands today.

1. How Scores Work

Each stock is scored daily on a scale of 0 to 100 using end-of-day price, volume, and fundamental data. The composite score combines four proprietary factor scores — Momentum, Value, Quality, and Financial Solidity — into a single number. The exact formula, component weights, and signal definitions are proprietary. Within each factor, stocks are ranked against the full universe and converted to a 0-100 percentile. The final composite score is the weighted average of these percentile ranks. Scores are classified using a traffic light system: - Strong (70-100): The stock ranks highly across most scoring dimensions. - Caution (40-69): Mixed signals — some factors positive, others weakening. - Weak (0-39): The stock ranks poorly across most scoring dimensions. This approach builds on the cross-sectional momentum factor first documented by Jegadeesh & Titman (1993), the Fama-French multi-factor framework (2015), and decades of research into value, quality, and financial health.
Strong70 – 100Ranks highly across scoring dimensions
Caution40 – 69Mixed signals
Weak0 – 39Ranks poorly across scoring dimensions

2. Our Scoring Approach

Our scoring approach draws on decades of academic research into price momentum, stock valuation, business quality, and financial health. Rather than relying on a single metric, the platform evaluates stocks across four complementary dimensions: - **Momentum:** Price trends across multiple timeframes, proximity to recent highs, and trading activity patterns that distinguish sustainable trends from short-lived spikes. - **Value:** Multiple valuation ratios grounded in research by Fama & French, Greenblatt, and O'Shaughnessy — designed to identify stocks trading below their intrinsic worth while avoiding value traps. - **Quality:** Profitability and capital efficiency metrics informed by Novy-Marx's profitability premium research, the Piotroski F-Score framework, and AQR's Quality Minus Junk factor. - **Financial Solidity:** Balance sheet strength indicators drawing on Altman's financial distress research and empirical evidence on leverage and stock returns. Each factor is grounded in peer-reviewed financial research. The specific combination of factors, their relative weights, and the signal construction methodology are proprietary. The multi-factor approach is designed to be more robust than any single measure. Academic research — notably Asness, Moskowitz & Pedersen (2013) and the Fama-French five-factor model (2015) — has shown that combining complementary factors reduces crash risk and improves consistency across different market environments.

3. Backtested Performance

The backtested results presented below apply exclusively to the momentum score. The current momentum formula (V2-C1) was selected after extensive backtesting across multiple candidate strategies, including signal-based and machine learning approaches. The chosen formula delivered strong risk-adjusted returns across Monte Carlo simulations with a broad global stock universe. The other scores — Value, Quality, and Financial Solidity — are not subject to a proprietary backtest. Their construction relies on methodologies extensively validated in academic literature: Fama & French (1992, 2015), Greenblatt (2005), and O'Shaughnessy (2011) for value; Novy-Marx (2013), Piotroski (2000), and Asness, Frazzini & Pedersen (2019) for quality; and Altman (1968) for financial solidity. These factors have been independently validated through decades of empirical research. Key momentum backtest results (median across Monte Carlo simulations): - Annualized return (CAGR): 30.6% - Sharpe ratio: 1.53 (range: 1.19 to 1.68) - Monthly hit rate: 66.0% - Maximum drawdown: 20.6% In practical terms, the strategy produced positive monthly returns roughly two out of every three months — but was negative one out of three. At its worst, the portfolio declined approximately 21% from peak to trough before recovering. The V2-C1 formula was specifically validated using Monte Carlo simulation to guard against survivorship bias — a common pitfall where backtests look better than reality because they only include stocks that survived. Several candidate strategies that appeared strong on a single-market backtest collapsed when tested against the broader universe. Backtest methodology: - Universe: 16,382 stocks from 14 global exchanges - Period: January 2010 to December 2025 (192 months) - Portfolio: 50 stocks, equal-weighted, rebalanced monthly - Transaction costs: 10 basis points round-trip - Validation: Monte Carlo simulation with random date sampling Important: These are hypothetical backtested returns, not live trading results. Past performance does not guarantee future results. Backtested data is subject to survivorship bias, as the stock universe is based on currently listed securities.

Median CAGR

30.6%

Sharpe Ratio

1.53

Range: 1.19 – 1.68

Monthly Hit Rate

66.0%

Max Drawdown

20.6%

Past performance does not guarantee future results. Hypothetical backtested results across Monte Carlo simulations, January 2010 – December 2025.

4. Limitations

A health check, not a crystal ball Scores measure relative positioning — how a stock ranks against its peers across multiple dimensions. A high score means strong performance relative to other stocks across momentum, value, quality, and financial solidity; it does not guarantee future performance. Momentum crash risk Momentum strategies can experience sharp, sudden losses during market regime changes. Research by Daniel & Moskowitz (2016) documented that momentum portfolios are vulnerable to "crashes" when markets reverse quickly — for example, during recoveries from bear markets. The momentum component of scores can drop rapidly during these events. Survivorship bias The backtested performance data uses a universe of currently listed stocks. Companies that were delisted due to bankruptcy, mergers, or other events are not included. This tends to make historical returns look slightly better than they would have been in real-time. No single score captures everything Even a multi-factor approach has blind spots. Factors like momentum, value, quality, and financial health are well-documented in academic finance, but no combination works in all market environments. Scores should not be the sole basis for investment decisions — they are one piece of a broader research process.

5. Frequently Asked Questions

How often are scores updated?
Scores are updated daily using end-of-day price, volume, and fundamental data. The scoring pipeline runs after market close, so scores reflect the most recent full trading day.
Why might a stock score change suddenly?
Earnings releases, sector rotations, broad market selloffs, or large volume spikes can all cause rapid score changes. Because scores are relative rankings against the full stock universe, a stock can also move if the stocks around it change significantly.
What does a low score mean?
A low score means the stock ranks poorly across the scoring dimensions relative to other stocks in the universe. It does not necessarily mean the stock is a bad investment — it may be in a temporary dip, undergoing a sector rotation, or simply not matching the factors we measure. Scores measure relative positioning, not absolute quality.
Is this financial advice?
No. MScore is an educational and informational tool. Scores reflect historical data and do not predict future performance. Nothing on this platform constitutes a recommendation to buy, sell, or hold any security. Always conduct your own research or consult a qualified financial advisor before making investment decisions.
How is this different from analyst ratings?
Analyst ratings are forward-looking opinions based on fundamental analysis — earnings forecasts, industry outlook, and company-specific factors. MScore scores are quantitative measurements based on historical price trends, valuation ratios, profitability metrics, and balance sheet health. They answer different questions: analysts try to predict where a stock is going, while our scores measure how a stock ranks today across multiple dimensions.
Why does trading activity matter for momentum?
Academic research shows that trading activity patterns can help distinguish sustainable momentum from short-lived spikes. Stocks in the early stages of a trend, with relatively quiet trading, tend to sustain their momentum longer than those experiencing heavy trading volume. This insight, documented by Lee & Swaminathan (2000), is one of many research findings incorporated into our scoring approach.
What is multi-factor scoring?
Multi-factor scoring evaluates stocks across several complementary dimensions rather than relying on a single signal. MScore scores stocks on four factors: Momentum, Value, Quality, and Financial Solidity. This approach is grounded in the Fama-French five-factor model (2015) and AQR's research showing that combining complementary factors produces more consistent risk-adjusted returns than any single factor alone. Each dimension captures a different aspect of a stock's attractiveness.
Does the score consider fundamentals beyond price momentum?
Yes. In addition to momentum, every stock is scored on three fundamental dimensions: Value (drawing on research by Fama & French, Greenblatt, and O'Shaughnessy), Quality (informed by Novy-Marx's gross profitability premium and Piotroski's F-Score), and Financial Solidity (based on Altman's distress research and leverage studies). These four factor scores are combined into a single composite score. The exact methodology remains proprietary.
What academic research underpins the scoring methodology?
The methodology draws on seminal work in quantitative finance: Jegadeesh & Titman (1993) on momentum, Fama & French (1992, 2015) on value and profitability factors, Novy-Marx (2013) on the gross profitability premium, Asness, Frazzini & Pedersen (2019) on quality, Piotroski (2000) on fundamental scoring, Greenblatt (2005) on combining value and quality, and O'Shaughnessy (2011) on composite valuation strategies. These papers collectively establish that multi-factor approaches outperform single-signal strategies.

Not investment advice. Read our disclaimer