Research for 10,031 US-listed stocks and ETFs.
See what a stock is worth, how it scores, and where it sits in the market.
Research and education — not investment advice.
Everything you need to research a stock, in one place.
Valuation, scoring, maps, charts and forecasts, all built on the same data and all showing their dates.
Fair value
The model that fits each company, and how far to trust it.
Explore →Market maps
Volatility and value across the whole market, in 3D.
Explore →Screener
Filter on valuation, growth, quality and technicals.
Explore →Chart overlays
Patterns, averages, bands and levels on the chart.
Explore →Analyze report
One click writes up the trend, the setup and what argues against it.
Explore →Price memory
Support and resistance weighted by where volume traded.
Explore →Forecasting
A 26-week range and the odds of each outcome.
Explore →Fundamentals
Twelve quarters of revenue, margins and cash flow.
Explore →A fair value built for how each company makes money.
A bank, a utility and a software company shouldn't be valued the same way. The engine picks the model that fits, works out the value, and tells you how much to trust it.
stocks valued, each by the model that fits how it makes money. Discount rates are worked out stock by stock.
Operating companies
Profitable businesses, on analysts’ revenue and margin forecasts when three or more cover them, otherwise their own record.
Cyclicals
Companies whose margins swing with the economy. With no analyst coverage, a mid-cycle DCF.
Banks and insurers
Lenders and insurers, valued on book value and the return they earn on it.
Loss-makers
Companies losing money today, valued on where analysts expect revenue and margins to go.
Utilities and REITs
Regulated utilities, property REITs and a few other steady payers, valued on the cash they pay out.
Investment vehicles
Business development companies and mortgage REITs, valued against their net assets.
Ocean shipping
Book value plus the returns analysts expect above the cost of capital.
Captive finance, alt managers
Manufacturers with a finance arm, and private-equity and credit managers.
Funds, holding companies
Closed-end funds and holding companies, valued on what they own.
Share classes, deals
A second share class takes the main listing’s value; an agreed takeover takes the deal price.
638 stocks
Losses with no usable forecast, financial distress or not common equity. The page says why instead of guessing.
Stocks valued by each model, 14 Nov 2026. Bars are relative to the largest group.
The engine's own value, from Apple's cash flows and its own discount rate.
Two opinions side by side. Neither is blended into the other.
Nearly nine in ten land within ±40% of analyst targets.
About six in ten do.
Fewer than four in ten do, or the engine flags a weak spot.
Apple (AAPL) on 13 Nov 2026. Confidence rates the method, not the company; agreement with analysts is a yardstick, not proof.
The whole market's volatility, as terrain.
450 companies, each raised by its 30-day realised volatility. Ridges are where the market is moving and basins are where it's calm. Every contour comes from real data, nothing smoothed for looks.
A screener where every filter actually filters.
Valuation, growth, profitability, leverage, liquidity, technicals and fund details, each tied to stored data and sortable. 10,031 stocks and ETFs.
| Ticker | Score | Price | Chg | P/E | To fair value |
|---|---|---|---|---|---|
| META | 623.61 | -0.82% | 22.8 | +66.5% | |
| MSFT | 523.00 | +0.36% | 27.4 | +26.1% | |
| AMZN | 267.44 | +0.48% | 20.4 | +0.4% | |
| AAPL | 359.69 | +1.36% | 36.1 | -32.1% | |
| GOOGL | 298.70 | +1.79% | 16.7 | +15.5% | |
| NVDA | 166.19 | -4.34% | 28.4 | +194.8% |
A golden cross here means the 50-day crossed above the 200-day in the last 15 sessions, not that it simply sits above it.
Every overlay shows its method.
Six overlays from the stock page, drawn by the same chart code on real tickers where they actually fire. Each panel names its settings, and a level nobody can source doesn't get drawn.
Daily candles with the volume histogram on its own scale — the analyze view as it opens
Volume is a separate price scale pinned to the lower 18% of the pane, so a heavy session never rescales the price it belongs to.
SMA 20 / 50 / 200, computed over full history rather than the visible window
A 65-bar window cannot produce a 200-day average. These are computed on the full series and then clipped to the view, which is why the 200-day line reaches the left edge instead of starting two thirds of the way in.
20-period SMA with the 1σ, 2σ and 3σ envelopes filled and the mid dashed
Live signal: bollinger_w_bottom, forming — a lower low in price that held above the lower band. Forming, not fired; the app labels the difference.
Double bottom, 113-bar scope, 65% confidence — forming, not triggered
The raw measured move is the 171.26 pattern height on the 691.52 neckline — 862.78. The app publishes 820.96, that move cut to 80%. It discounts its own target and says by how much.
Decayed support and resistance bands, plus the point of control
Band opacity is the level’s strength, and the 275.62 band carries a flip marker because it used to be resistance. Long-horizon bands are drawn at half weight so a year-old level cannot shout as loudly as last month’s.
Separate panes, as the app stacks them — RSI(14) Wilder, MACD 12/26/9
Both are off by default. The RSI states its smoothing convention on the page, because a Wilder RSI and a simple-average RSI disagree by several points on the same bars.
Bars through 9 Sep 2026. Apple had no nameable pattern on these bars, so the pattern panel uses Meta. On the stock page the crosshair reads out every value under the cursor.
One click, and the whole write-up.
Trend, structure, pattern, indicators and trigger on one page, the valuation beside them, and a closing paragraph that names what argues against the move as readily as what argues for it.
Support and resistance, decayed by turnover.
Most tools draw a line where price bounced once. This maps everywhere the market actually traded and lets old levels fade with turnover, not the calendar. Every band says what built it.
The invalidation isn't a round number someone picked — it is the 300.86 support band above, the strongest short-horizon level in the field. Reward-to-risk on that pair is 2.81, and the tool prints the ratio rather than only the upside.
Two setups, and the tool publishes the bad one too. The anchored-VWAP entry sits 18 cents above its own stop, so its reward-to-risk is 0.09 — a ratio that says don't. Filtering it out would have made the screen look better and the research worse.
Research and education. Not investment advice, and not a recommendation to buy or sell anything.
| Level | Role | Touches | Last touch | Built from | History |
|---|---|---|---|---|---|
| $344.44 | ▼ resistance | 3 | 29 bars | pivots · extreme · round | resistance |
| $316.92 | ▼ resistance | 6 | 13 bars | pivots · volume · round | resistance |
| $300.86 | ▲ support | 8 | 19 bars | pivots · volume · round | mixed |
| $275.62 | ▲ support | 14 | 52 bars | pivots · volume | flipped from resistance |
| $225.92 | ▲ support | 14 | 250 bars | pivots · volume · extreme | mixed |
Built on published research: Osler (2000, 2003), Kavajecz & Odders-White (2004), Grinblatt & Han (2005), George & Hwang (2004) and Donaldson & Kim (1993).
Where the market is moving, sector by sector.
Median one-month return for each sector. The median, so one giant can't carry a whole sector.
A range and its odds, not a price target.
For about 3,500 US stocks, a four-step model estimates where the price could be in 26 weeks, how likely each outcome is, and the probability-weighted value. We tested it on 352,191 historical forecasts and publish the misses next to the passes.
Factor regression
Measures how each stock moves with six market-wide factors (market, size, value, profitability, investment, momentum) and how much it moves on its own.
Bootstrap simulation
Simulates possible 26-week paths for those factors by resampling real market history in blocks, so streaks and crashes stay in.
Monte Carlo
Combines each stock's exposures with the shared paths and adds a stock-specific shock sized to its own volatility.
Scenarios and value
Reads the simulated outcomes as a price range, the chance of each return zone, and a probability-weighted expected value.
Over 12 months the expected value is $390 (+14.3%) against an analyst median target of $362. The model gives a 55% chance of finishing above that target. The expected value sits above the median because compounding skews outcomes to the right.
| Test | All stocks | Large caps |
|---|---|---|
| Outcomes inside the 90% range | 89.0%pass | 91.0%pass |
| Outcomes inside the 95% range | 93.2%miss | 95.0%pass |
| Same 90% test, own-history shortcut | 75.1%miss | — |
| Beats a market-only version | tie | tie |
| Stock-specific alpha adds accuracy | no | no |
The pass/fail rules were written before the test ran, and the test data was used once. Delisted stocks are included. The miss on the 95% range is small-cap crash risk: drops below the range came 3.7% of the time instead of 2.5%. A market-only version did just as well, so that simpler model is the one going into the live test.
The six factors are rebuilt from raw prices and filings, not downloaded. Backtested results are hypothetical: they show how the model would have done, not a live track record. Research and education — not investment advice.
The markets page and the stock page.
Markets is the first screen after you sign in, and the stock page is where every ticker lands. Captured from the app on 30 Sep 2026; scroll inside a frame to see more.
Twelve quarters, straight from the filings.
Revenue, margins, earnings, cash flow, dividends and share count, quarterly or annual. Apple below, drawn by the stock page's own chart code.
EPS
Revenue
Free cash flow
Earnings surprise
Revenue & gross profit
Shares outstanding
Dividends
Operating margin
Every card opens full-screen with the full history the plan allows, and the axis is left alone: the one red bar on Earnings surprise is a real 2.6% miss in February 2023, and Apple's June-2026 quarter is the last one that has reported — the unreported quarter after it is absent rather than drawn as a zero.
Twelve crypto assets, the same chart engine.
The same charts and indicators, and the same honesty about partial bars: the 30-day change is measured to the last complete day, never a half-formed one.
| Asset | Last close | 30-day | Basis |
|---|---|---|---|
| BTC | $78,447.11 | ▲ +21.0% | Bitcoin · last complete daily bar |
| ETH | $2,485.02 | ▲ +30.2% | Ethereum · last complete daily bar |
| SOL | $103.37 | ▲ +35.6% | Solana · last complete daily bar |
| XRP | $1.42 | ▲ +37.7% | XRP · last complete daily bar |
| DOGE | $0.09 | ▲ +30.1% | Dogecoin · last complete daily bar |
13,865 securities, broken out by type.
One big number would hide what you actually get, so here it is by instrument.
| Instrument | Count | Quant score | Fair value | What you get |
|---|---|---|---|---|
| Stocks | 6,296 | 5,885 | 2,658 | Score, sub-scores, a fair value where a model qualifies, full technicals |
| ETFs | 3,735 | Not scored | Not valued | Holdings, expense ratio, AUM, sector mix and technicals. An equity score on a fund would mean nothing, so we don't publish one |
| Mutual funds | 3,834 | Not scored | Not valued | Quotes and profile only. They don't trade on an exchange, so we don't count them as listed |
Counted 13 Nov 2026. A stock the engine can't value with confidence reads not valued, never a placeholder number.
The rules we build to.
Four rules every page follows.
A number we can't source doesn't ship
Where a value is missing the page says "not reported" or "not valued" and never fills the gap with a default.
Nothing here is written by a language model
Scores, values, indicators and patterns are computed from stored market and filing data. Commentary, where it appears, is labelled as commentary.
Every figure carries its date
Prices are stored daily closes refreshed each session, not a live feed, and the page tells you which session you're reading.
We describe, we don't advise
No buy or sell ratings, no targets of our own, no personalised guidance. The tool measures; what you do with it is yours.
Research you can audit.
A quant score on 5,885 stocks, a fair value on 2,658 of them, and a methodology page that matches the code.
Free during beta. No card required.