The signal engine

Meet the Oracle

The Oracle is the machine-learning model behind every trade you take. It never pulls the trigger for you. It hands you one honest read on each ticker you watch, a few times a day, so you can stop second-guessing and act with an edge. Here is exactly what goes into that read.

Scroll
Anatomy of a signal

Every card carries seven decisions

Scroll slowly. The card stays put while it comes apart, one piece at a time.

NVDAMarket open
×
BUY CALLSB
96%(conf.)
82% est. win rate
96% . 0s ago
Regime: bull
$199.76
15:26:44
Next 5 min
59%
Mild upside lean
Details & indicators
Log Trade
  1. 1
    Calls or puts

    The Oracle is symmetric. It reads downside as readily as upside, so a bearish setup surfaces as BUY PUTS, not just a shrug.

  2. 2
    Raw ensemble confidence

    Five independent engines - trend, institutional flow, momentum, news sentiment, and a prediction layer - vote on every ticker. Their weighted blend is this raw score.

  3. 3
    Calibrated win rate

    The raw score is re-mapped against thousands of real outcomes, so this number tracks how often signals at this confidence actually worked out, not how loud the model is.

  4. 4
    Conviction tier

    A, B, or C grades the setup. The tier scales position size with a half-Kelly rule, so the model leans in only when the edge is clearer.

  5. 5
    Live and time-stamped

    Every card carries the real-time price and the exact second it was computed. Signals refresh through the session, not once a day.

  6. 6
    Regime aware

    It reads the wider market first. In a bull tape it leans in; in a bear tape it asks for more evidence before it says buy.

  7. 7
    The next five minutes

    A short-horizon read layered on top: a quick lean for the minutes just ahead, learned from how similar setups resolved.

Your watchlist

Seventeen tickers, one deck

NVDAMarket open
×
BUY CALLSA
96%(conf.)
82% est. win rate
96% . 0s ago
Regime: bull
$199.76
15:26:44
Next 5 min
59%
Mild upside lean
Details & indicators
Log Trade
NQMarket open
×
BUY CALLSB
93%(conf.)
76% est. win rate
93% . 2m ago
Regime: bull
$22380.25
15:26:38
Next 5 min
61%
Trend intact
Details & indicators
Log Trade
QQQMarket open
×
BUY CALLSC
91%(conf.)
67% est. win rate
26% . 23m ago
Regime: bull
$736.44
15:26:11
Next 5 min
61%
Mild upside lean
Details & indicators
Log Trade
ESMarket open
×
BUY CALLSA
90%(conf.)
71% est. win rate
90% . 4m ago
Regime: bull
$6142.50
15:25:52
Next 5 min
60%
Grinding higher
Details & indicators
Log Trade
AAPLMarket open
×
BUY CALLSB
88%(conf.)
74% est. win rate
88% . 1m ago
Regime: bull
$232.14
15:26:30
Next 5 min
60%
Mild upside lean
Details & indicators
Log Trade
METAMarket open
×
BUY CALLSA
87%(conf.)
72% est. win rate
87% . 3m ago
Regime: bull
$632.10
15:26:02
Next 5 min
59%
Mild upside lean
Details & indicators
Log Trade
NFLXMarket open
×
BUY CALLSB
83%(conf.)
66% est. win rate
83% . 5m ago
Regime: bull
$1043.60
15:25:44
Next 5 min
58%
Mild upside lean
Details & indicators
Log Trade
TSLAMarket open
×
BUY CALLSBContrarian
81%(conf.)
65% est. win rate
81% . 2m ago
Regime: bull
$351.40
15:26:19
Next 5 min
57%
Squeeze setup
Details & indicators
Log Trade
SPYMarket open
×
BUY CALLSB
79%(conf.)
64% est. win rate
79% . 6m ago
Regime: bull
$611.28
15:25:33
Next 5 min
57%
Mild upside lean
Details & indicators
Log Trade
AMZNMarket open
×
BUY CALLSC
77%(conf.)
63% est. win rate
77% . 4m ago
Regime: bull
$228.40
15:25:58
Next 5 min
56%
Mild upside lean
Details & indicators
Log Trade
INTCMarket open
×
BUY PUTSBContrarian
74%(conf.)
59% est. win rate
74% . 3m ago
Regime: bear
$34.22
15:26:07
Next 5 min
57%
Slight downside
Details & indicators
Log Trade
MSFTMarket open
×
BUY PUTSB
71%(conf.)
58% est. win rate
71% . 1m ago
Regime: bull
$372.83
15:25:57
Next 5 min
55%
Slight downside
Details & indicators
Log Trade
VIXMarket open
×
BUY CALLSC
68%(conf.)
56% est. win rate
68% . 8m ago
Regime: volatile
$15.80
15:25:20
Next 5 min
58%
Vol ticking up
Details & indicators
Log Trade
AMDMarket open
×
BUY PUTSC
66%(conf.)
55% est. win rate
66% . 5m ago
Regime: bear
$168.75
15:25:41
Next 5 min
56%
Slight downside
Details & indicators
Log Trade
ORCLMarket open
×
BUY PUTSD
63%(conf.)
54% est. win rate
63% . 7m ago
Regime: bull
$178.90
15:25:29
Next 5 min
54%
Fading
Details & indicators
Log Trade
GOOGLMarket open
×
HOLDC
52%(conf.)
51% est. win rate
52% . 9m ago
Regime: neutral
$191.20
15:25:14
Next 5 min
-
Balanced, no edge
Details & indicators
Log Trade
IWMMarket open
×
HOLDC
49%(conf.)
50% est. win rate
49% . 11m ago
Regime: neutral
$231.55
15:25:03
Next 5 min
-
Balanced, no edge
Details & indicators
Log Trade
NVDA96% BUY CALLS, tier A
01 / 17
01 - The ensemble

Five engines, one vote

There is no single black box. Five independent engines each score the same ticker from a different angle, and the Oracle blends them by weight. No engine can carry a trade alone.

Institutional flow
22%
Momentum
22%
Prediction layer
20%
Trend and technicals
18%
News sentiment
18%
-Institutional flow: Support and resistance, VWAP, volume nodes
-Momentum: Rate of change, stochastics, on-balance volume
-Prediction layer: A trader-style synthesis of the setup
-Trend and technicals: Moving averages, RSI, MACD, bands
-News sentiment: The tone of recent headlines
Composite score
The weighted blend of all five
Calibration
Mapped to real win rates
Profitability gate
Only strong setups surface
02 - Honest confidence

The number you can trust is the calibrated one

A raw model score is easy to inflate. So the Oracle re-maps every score against thousands of past outcomes with isotonic regression. A calibrated 70 means signals at that level actually resolved in your favour about seven times in ten. That is the small emerald line on the card, and it is the number that actually matters.

Raw confidence

How loudly the ensemble is shouting. Useful, but it can be miscalibrated.

Calibrated win rate

The same score, corrected against real history. This is the honest read.

03 - Regime and sizing

It reads the room, then sizes the bet

Before it scores a single ticker, the Oracle classifies the broader market as bull, bear, or neutral from the index trend and volatility. In a bear tape it raises the bar to call a buy and lowers it to call a sell. The conviction tier then translates directly into size.

A
Full conviction

Clearest edge. Largest position under a half-Kelly rule.

B
Solid

The everyday signal. A measured, baseline position.

C
A whisper

Worth noting, sized small. Often skipped entirely.

04 - It improves itself

A quiet loop that runs every night

After the close, the model re-grades itself on the day it just lived through, retrains a challenger, and tests it on data it has never seen. The challenger only takes the crown if it genuinely beats the reigning model out of sample, after trading costs. Each champion gets a name, so upgrades are easy to track over time.

1
Re-grade

Score the freshest outcomes and grow the training set.

2
Challenge

Train a rival and test it on untouched, future data.

3
Promote with guardrails

Swap only if the rival wins after costs. Otherwise, no change.

05 - How it is measured

Graded the way a skeptic would

We would rather show you the method than a flattering headline number. Here is how every version of the model earns its place.

Clear win and loss lines

Each signal is labeled by whether a fixed profit target, a fixed stop, or a time limit hit first. No cherry-picking the exit.

Tested on the future, not the past

The model trains on older data and is scored only on newer data it never saw, so results are not memorised.

Costs come out first

Commissions and slippage are subtracted before anything counts. The bar is beating the cost of trading, not zero.

Calibration, checked

Predicted confidence is plotted against what actually happened. The closer to the diagonal, the more honest the number.

PredictedActual
Reliability, not bravado

A calibration curve is the plainest test of an honest model. Each point compares what the model predicted with what really happened. The dashed line is perfect calibration. The whole aim of the calibration step is to pull the model onto that line. The axes here carry no numbers on purpose, because this shows the method, not a performance claim.

A note on honesty: the Oracle is a research tool, not financial advice, and not a promise. Signals are one input into a human decision. Markets change, models drift, and past behaviour does not guarantee future results.

See the Oracle read a live ticker

Watch the card update in real time and decide for yourself. Free during the open beta.