Methodology
How TrendMatrix
scores stocks.
Most stock screeners output filters — a list of names that match a ratio threshold. Most paid screeners cost $30 per month or more, and quality factors are scattered across half a dozen tools. TrendMatrix scores 2,500+ US stocks across ten dimensions every night, runs the survivors through an eleven-gate expert panel, and publishes one of four verdicts with an entry target, take-profit, stop-loss, and risk/reward ratio. The site is the product. There is no signup and no paid tier.
This page is the long form. It explains every score, every gate, and every verdict label. If you want the short version, the about page covers the founder story and the pricing comparison.
The 10 dimensions
Each stock receives a 0–10 score on ten dimensions. The composite score is a weighted sum: value, quality, and growth at 15% each; momentum, sentiment, insider, and peer rank at 10% each; technical, risk, and catalyst at 5% each. The weighting biases toward fundamentals over technicals, and toward business reality over short-term flow.
Value (15%)
What you pay relative to what the business produces. Inputs: trailing P/E, forward P/E, P/S, P/B, EV/EBITDA, free-cash-flow yield, PEG ratio, and analyst consensus target with a coverage-tiered haircut. The dimension blends 40% trailing signals with 60% forward signals so a name with a strong 12-month outlook is not punished for a weak last quarter. REITs use P/OCF instead of P/E because depreciation add-backs make GAAP earnings structurally misleading. A stock with a forward P/E under 15 and a positive free-cash-flow yield typically scores 8 or higher on value; a stock with a forward P/E above 60 and negative cash flow typically scores below 4.
Quality (15%)
How profitable and well-capitalized the business is. Inputs: return on equity, return on assets, gross margin, operating margin, net margin, debt-to-equity, current ratio, interest coverage, and the Piotroski F-score. A company compounding capital at 25%+ ROE on healthy margins scores at the top of the range; a thin-margin business carrying excessive leverage scores at the bottom.
Growth (15%)
How fast the top and bottom lines are expanding. Inputs: year-over-year revenue growth, earnings growth, and last-quarter EPS surprise versus consensus. Strong growth (20%+ YoY) earns a note; declining revenue earns a flag. The dimension is unweighted across components — beating estimates by 10% counts the same as growing 20% YoY.
Momentum (10%)
Whether price action confirms or contradicts the fundamental view. Inputs: RSI(14), MACD line and histogram, position versus the 20/50/200-day moving averages, and volume ratio. The RSI interpretation is context-aware — an RSI of 35 in an uptrend (above 200-day MA) reads as a buyable pullback and scores 7+; the same RSI in a downtrend reads as a falling-knife risk and scores 3.5.
Sentiment (10%)
What the news flow and analyst community are saying. News sentiment is computed from the last 30 days of headlines, with articles pre-scored by an LLM and recency-weighted so a two-day-old story counts more than a 25-day-old one. Analyst signal is structured: target-price moves, upgrade/downgrade actions, and consensus distribution all feed the score separately. A stock with positive headlines and a tightening analyst consensus around a higher target scores well.
Insider (10%)
What the people closest to the business are doing with their shares. Inputs: net dollar value of insider trades over the last 90 days as a percentage of market cap, with a C-level amplifier and a buy/sell ratio. A CEO buying 0.5%+ of market cap on the open market scores at the top; a cluster of C-level sellers above 0.5% of cap scores at the bottom. The Finnhub "BULLISH/BEARISH" categorical signal is ignored — three small routine sales should not look the same as a $50M CEO dump.
Peer Rank (10%)
Where the stock sits inside its industry. Each industry cohort is scored on value, quality, and growth, and the stock is ranked 1-of-N within its peer group. A best-in-class operator gets a positive note; a worst-in-class operator gets flagged as lagging peers. The ranking is what powers the "#8 of 80" label on the stock page.
Technical (5%)
Chart-level entry quality. Inputs: Bollinger band position, distance from support and resistance, ATR (average true range) as a percent of price. A stock trading near support with low realized volatility scores well; a stock pinned to upper Bollinger with a wide ATR scores poorly.
Risk (5%)
What can blow up. Inputs: short interest as a percentage of float (with a quality-conditional read — high short on a high-quality name reads as squeeze setup, high short on a low-quality name reads as justified-bear), beta versus the S&P 500, recent volatility, options put/call skew, and a concentration component derived from 10-K stock-intel extraction (each HIGH-severity concentration takes 2.5 points off the dimension). Sector floors apply: Healthcare gets a lower bar (biotech volatility is structural), Utilities and Consumer Defensive get a tighter one (a defensive name with a weak risk score is unusual).
Catalyst (5%)
What is about to move the stock. Inputs: earnings revision momentum (analyst EPS estimate change over 30 and 90 days), proximity to the next earnings date, recent material news, and beat/miss streak. Estimates revising up by 5%+ over 30 days add 2.5 points to the catalyst score; estimates revising down by 5%+ subtract 2.5.
The V9 expert panel
A 7.5/10 score is not enough. The fundamentals can be excellent and the timing or setup wrong. The V9 expert panel is the layer that catches that. Eleven gates run after the score is computed. Any gate failure can downgrade a strong-score stock from STRONG_BUY_NOW to STRONG_BUY_WAIT (or further, if the failure is severe). The philosophy is simple: a stock can be a great business at a bad moment, and the verdict should reflect that.
- ASYMMETRY — the risk/reward ratio at the entry price must be ≥1.5. A stock with 5% upside and 5% downside does not clear, regardless of score.
- MOMENTUM — the momentum dimension must score ≥4.5. A stock with great fundamentals but a chart in active breakdown is a wait, not a buy.
- DEATH_CROSS — the 50-day moving average below the 200-day moving average is a hard block. Trend structure matters even when fundamentals look fine.
- INSIDER — the insider dimension must clear the floor (currently 2.5). Heavy C-level selling above 0.5% of market cap blocks BUY_NOW regardless of score.
- 8K:CLEAN — no recent material 8-K red flag. Auditor changes, earnings restatements, and bankruptcy filings are hard blocks.
- NEWS_EVENTS — no recent material negative event in the news feed. CEO transitions, regulatory probes, and product recalls trigger this gate.
- SEMI_CYCLE_PEAK — applies only to Tech and Semiconductors. A forward P/E under 10 combined with a forward/trailing P/E ratio under 0.30 means EPS just exploded off a trough — the classic memory-semi cycle peak signature. Catches MU cleanly without false-flagging NVDA or AMD.
- REIT_TENANT — applies only to Real Estate. A single tenant ≥40% of net operating income is a concentration cliff. Net-lease REITs disclose this as a policy risk factor at the same threshold.
- HEALTHCARE_PAYER — applies only to Healthcare. Government payer (Medicare, Medicaid, CMS) ≥70% of revenue is a reimbursement cliff. CMS rate changes have driven 50%+ drawdowns in pure-play government-payer names.
- GEO_CONCENTRATION — applies only to Financial Services. A single state or shared regional cluster ≥60% of book is a geographic cliff. Anchored in regional-bank distress literature: Texas 1986, Florida 2008, the New York regional cluster in 2023.
- EARNINGS_PROXIMITY — within 7 calendar days of the next earnings print, BUY_NOW becomes BUY_WAIT. The 8-to-14-day window gets a visible warning with no block. Median S&P names realize roughly 80% of their earnings-driven move in the five trading days around the print.
- Value-trap heuristic — when the forward P/E is much higher than the trailing P/E, earnings are about to compress. The "cheap" valuation is a mirage and the gate flags it.
A gate failure does not always send the verdict to SELL. Most of the time it flips STRONG_BUY_NOW to STRONG_BUY_WAIT — the engine is saying "this is still a good company, just not at this price or this moment".
The stock-intel layer
Stock-intel is a separate pipeline that reads the 10-K (annual report) for every name in the universe and extracts structured concentrations: supplier dependencies, customer concentration, geographic exposure, regulatory exposure, and counterparty risk. 8-K material events (auditor changes, executive departures, restatements, bankruptcy) come from EDGAR.
Coverage today: 100% of the universe has stock-intel populated. Roughly 34% of stocks (861 of 2,500+) flag at least one HIGH-severity concentration. The data feeds two consumers. The universal Risk dimension takes 2.5 points off for each HIGH-severity concentration. The sector-specific V9 gates (REIT_TENANT, HEALTHCARE_PAYER, GEO_CONCENTRATION) read the same data and fire only when the cliff threshold is crossed inside the relevant sector.
Concrete example: NVIDIA flags TSMC as a MEDIUM-severity supplier concentration. NVDA depends on TSMC for fab capacity, and the 10-K discloses it as a risk factor — that is the kind of fact stock-intel surfaces structurally rather than asking you to read footnotes.
What each verdict means
- STRONG_BUY_NOW — the score is high, every V9 gate passed, the asymmetry is positive at the entry price, and the recent setup confirms the entry. The model thinks now is a reasonable time to start a position at the current price.
- STRONG_BUY_WAIT — the score is high but at least one entry condition is missing. Most often the price has not pulled back to entry yet, or earnings are within 7 days, or a moving-average gate is firing. Watch the stock; do not chase it.
- HOLD_IF_HOLDING — not a fresh buy candidate. If you already own it there is no urgent reason to sell, but the model would not buy more at this price.
- SELL_IF_HOLDING — the score is weak, a critical gate has failed, or news and filings are flashing red. Consider reducing exposure.
Be honest with yourself about what these labels are. They are educated opinions from a model that reads the same public data you can read, applied consistently across every name. They are not guaranteed outcomes.
What this is not
- Not investment advice. TrendMatrix produces model-generated quantitative analysis for informational purposes only. InsightMatrix LLC is not a registered investment advisor. Consult a qualified financial professional before making investment decisions.
- Not a backtest. The site does not publish historical alpha claims. The model is run forward in time, and the public verdict ledger is the only record of what it said when.
- Not optimized for dividends. The current dimensions weight total-return signals (price, earnings, growth) heavily and yield lightly. A dividend-first version of the score is on the backlog, not in production.
- Not for day-trading. Signals refresh every 5 minutes during market hours, not in real time. Intraday momentum and order-flow signals are out of scope.
- Not a meme-stock detector. The model is conservative by design. It will not catch every breakout in a name with no fundamentals, and it actively downgrades stocks where the only bull case is technical.
How it stays fresh
The full pipeline runs nightly at 2:30 AM ET. Phase 1 pulls fundamentals; Phase 2 pulls insider transactions and analyst recommendations in parallel; Phase 3 runs the deep analyzer that produces every score, every gate, and every verdict. During market hours, a Phase 3 delta refresh re-runs every 5 minutes against current prices to keep entry-target distance, risk/reward ratios, and verdict labels in phase. News and sentiment update on the same 5-minute cadence. Every published row is stamped with the algo version (currently v9.4.0) so before-and-after comparisons across engine evolutions stay interpretable.