Scores are algorithm-generated research tools, not investment recommendations.
How AlphaStocks Scores Every Stock
The Problem with Traditional Screeners
Most stock screeners hand you a spreadsheet of raw numbers — P/E ratios, ROE, debt-to-equity — and wish you luck. You end up comparing a bank to a software company using the same yardstick, cherry-picking whatever metric confirms your bias, and calling it “research.”
That is not analysis. That is data with a search bar.
The real question is not “what are the numbers?” It is “what do the numbers mean, taken together, for this specific kind of business, right now?”
AlphaStocks answers that question. We evaluate every S&P 500 company through five time-tested investment methodologies, combine them into a single composite score from 0 to 10, calibrate for sector, and validate the result on data the formula has never seen.
The Four-Axis Composite Score
Every stock receives a score on four axes. Each axis answers a distinct question about the company. The composite score is a weighted blend of all four:
Composite = Quality × 0.40 + Value × 0.15 + Price Trend × 0.25 + Timing × 0.20| Axis | Weight | Question It Answers | Source Models |
|---|---|---|---|
| Quality | 40% | Is this a strong, durable business? | Piotroski F-Score (35%) + Buffett-Style Moat (65%) |
| Value | 15% | Is the stock priced below what it is worth? | Graham Fair Value (45%) + Lynch PEG (25%) + Greenblatt Magic Formula (30%) |
| Price Trend | 25% | Is the price moving in the right direction? | 6-month price momentum, percentile-ranked within S&P 500 |
| Timing | 20% | Is the stock cheap AND rising at the same time? | min(Value, Price Trend) |
Why these weights? Because decades of academic research and practitioner experience point to the same conclusion: business quality is the strongest long-term predictor of stock returns, but entry price and momentum determine whether you actually capture that return or spend two years underwater.
Axis 1: Quality (40% of Composite)
What it measures: Financial health, profitability, competitive durability — the characteristics that separate companies that compound wealth from those that destroy it.
Why it gets the largest weight: A great business bought at a fair price almost always outperforms a mediocre business bought at a bargain. Quality compounds. Cheapness does not.
How it is built: The Quality axis blends two complementary models:
Piotroski F-Score (35% of Quality)
Nine binary signals covering profitability (positive net income, positive operating cash flow, improving ROA), leverage (declining debt, improving current ratio, no dilution), and efficiency (improving gross margin, improving asset turnover). Each signal is either 0 or 1. A score of 7-9 indicates strong financial health; 0-3 suggests distress.
Buffett-Style Quality Assessment (65% of Quality)
A broader, judgment-oriented evaluation inspired by Warren Buffett's investment philosophy. It examines ROE consistency over multiple years, operating margin stability, manageable debt relative to earnings, and earnings predictability. The output is a five-tier rating: Strong, Attractive, Neutral, Reject, or Insufficient Data.
A company needs to score well on both to earn a high Quality rating. A single great year does not fool the system, and one bad quarter in a decade of excellence does not penalize it unfairly.
Axis 2: Value (15% of Composite)
What it measures:Whether the stock's current market price is above, below, or near its intrinsic worth as estimated by three independent valuation frameworks.
Why it gets a modest weight: Value alone is dangerous. A stock can look cheap for years while the business deteriorates. The Value axis matters, but it is deliberately constrained to prevent the formula from chasing falling knives.
Graham-Style Fair Value (45% of Value)
Calculates an estimated intrinsic value using earnings, growth rates, and a margin of safety, inspired by the framework Benjamin Graham outlined in The Intelligent Investor. The output includes conservative, base, and optimistic scenarios.
Lynch-Style PEG Analysis (25% of Value)
Peter Lynch argued that a stock's P/E ratio should be compared to its earnings growth rate. A PEG ratio below 1.0 suggests the market is underpricing the company's growth. Our implementation adjusts for dividends and classifies each company into Lynch's categories: Fast Grower, Stalwart, Slow Grower, Turnaround, Asset Play, or Cyclical.
Greenblatt-Style Magic Formula (30% of Value)
Joel Greenblatt's approach ranks stocks by two criteria — earnings yield and return on invested capital. Companies that rank highly on bothdimensions are “good businesses at good prices.” We percentile-rank every S&P 500 stock against its peers.
Axis 3: Price Trend (25% of Composite)
What it measures:The direction and strength of a stock's price movement over the past six months, ranked against every other stock in the S&P 500.
Why it matters: Markets are not perfectly efficient. Stocks that are rising tend to keep rising in the medium term, and stocks that are falling tend to keep falling. This is one of the most robust findings in empirical finance.
Price Trend serves two purposes: it captures market intelligence (rising prices often reflect information not yet in quarterly filings), and it acts as a timing filter — a stock may be fundamentally excellent, but if the market is actively selling it, something may be wrong.
Axis 4: Timing (20% of Composite)
What it measures: Whether a stock is simultaneously undervalued and gaining momentum.
Timing = min(Value, Price Trend)This single axis is the formula's value-trap killer. If Value is high but Price Trend is low, Timing collapses to the lower of the two. The stock cannot score well overall until the market confirms the value thesis by actually bidding the price higher.
The sweet spot is where both are elevated: cheap AND rising. That is where the Timing axis rewards you.
Safeguards: If Value scores 7.0+ and Price Trend scores 3.0 or below, a value trap warning is displayed. If Price Trend falls below 2.5, the composite score is capped at 6.0 regardless of other axes.
Sector-Specific Calibration
A bank should not be evaluated the same way as a cloud software company. AlphaStocks uses seven sector-specific scoring profiles:
| Profile | Applied To | Key Differences |
|---|---|---|
| General | Technology, Consumer, Healthcare, Industrials | Standard weights across all models |
| Bank | Commercial and investment banks | Higher Buffett weight (moat + deposit franchise) |
| REIT | Real Estate Investment Trusts | Graham uses FFO; higher momentum weight |
| Insurer | Insurance companies | Piotroski adapted for float-based model |
| Utility | Electric, gas, water utilities | Higher dividend/stability weight |
| Holding | Conglomerates | Adjusted for diversified revenue streams |
| Asset Manager | Investment managers, brokerages | Adapted for AUM-driven revenue |
When you see a bank scored at 8.0 and a tech company scored at 8.0, they earned those scores through genuinely comparable processes, not by being forced through the same generic filter.
Walk-Forward Validation: Does It Actually Work?
We designed the scoring formula using market data from January 2021 through December 2023. Then we locked the formula and ran it on data from January 2024 through February 2026 — a period the formula had never seen during development. This is called walk-forward (out-of-sample) validation.
| Period | Top-30 Portfolio* | S&P 500 (SPY) | Alpha | Sharpe |
|---|---|---|---|---|
| In-sample (2021-2023) | +48.2% | +34.4% | +13.9% | 0.61 |
| Out-of-sample (2024-2026) | +51.8% | +45.6% | +6.2% | 1.12 |
| Full period (2021-2026) | +132.9% | +98.7% | +34.2% | 0.84 |
*Hypothetical backtested results. Top-30 portfolio = 30 highest-scoring stocks, rebalanced monthly. Simulated, not actual trading. Does not include transaction costs, taxes, or slippage.
The out-of-sample Sharpe ratio of 1.12 is actually higher than the in-sample Sharpe of 0.61. That is the opposite of what you see with overfit strategies.
Maximum drawdown: 14.3% for the Top-30 portfolio vs 23.9% for the S&P 500 — roughly 40% less peak-to-trough pain.
What the Score Labels Mean
| Score | Label | What It Signals |
|---|---|---|
| 8.5 - 10.0 | Strong Buy | Exceptional across all four axes. Typically fewer than 20 stocks at any time. |
| 7.0 - 8.4 | Buy | High-quality, attractively valued, with positive momentum. |
| 5.5 - 6.9 | Hold | Decent fundamentals but not compelling on value or momentum. |
| 4.0 - 5.4 | Neutral | Mixed signals across models. No clear advantage over the index. |
| 2.5 - 3.9 | Below Average | Weakness in multiple axes. Fundamentals or momentum raising concerns. |
| 0.0 - 2.4 | Avoid | Low scores across the board. Multiple models flagging problems. |
What the Formula Does Not Do
Transparency means being honest about limitations:
- It does not predict the future. Past performance does not guarantee future results.
- It underperforms in sideways markets. In 2024-2026 sideways periods, the Top-30 returned -3.2% while the S&P 500 returned +3.0%.
- It is backward-looking. Financial data comes from SEC filings, which report past performance.
- It does not capture qualitative factors. Management character, pending lawsuits, regulatory shifts, geopolitical risks.
- Individual stock risk is not eliminated. The backtest shows results for a portfolio of 30 stocks. Individual outcomes have much wider variance.
- The backtest is simplified. Monthly rebalancing with no transaction costs, taxes, or slippage modeled.
How to Use AlphaStocks Scores
- Screen: Sort by composite score or filter by sector, model status, or individual axis.
- Investigate: Read the signal breakdowns. Understand why each model rates the stock the way it does.
- Contextualize: Does the thesis make sense given what you know about the company and the current market?
- Decide: Make your own decision based on the full picture — the score, your research, your risk tolerance.
The score does the quantitative heavy lifting. The judgment is yours.
Explore Individual Models
Model names reference the published investment methodologies of their respective authors. AlphaStocks is not affiliated with, endorsed by, or sponsored by Warren Buffett, Berkshire Hathaway, Peter Lynch, Fidelity Investments, Joel Greenblatt, Gotham Asset Management, or the estates of Benjamin Graham or Joseph Piotroski. Our implementations are interpretations of publicly described principles and may differ from the original authors' approaches.
AlphaStocks provides investment research and analysis, not investment advice. Past performance does not guarantee future results. Always do your own due diligence before making investment decisions. Data sourced from SEC EDGAR and Alpaca Markets.