AI that simplifies markets
Gold· 12 days
Example
Could Gold go up 1% within 12 days?
84%
Kunkafa’s confidence in reaching it
↓ Down 0.6% in the same period: Kunkafa’s confidence: 70%
Either, both or neither could happen.
Probability, Not Prophecy. Forecast, not advice.
One forecast. Three ways to read it.
From one question to the full view. Same numbers, three readers.
Your market, your duration, a round threshold; Kunkafa’s confidence, then the other side below it.
Every move from one point: right is more time, up or down is a bigger move, solid dots are likelier.
The price line, the forecast band, and every level with Kunkafa’s confidence.
Gold· 12 days
Example
- 01 · Market Gold
- 02 · Duration 12 days
- 03 · Distance 1%
Could Gold go up 1% within 12 days?
84%
Kunkafa’s confidence in reaching it
↓ Down 0.6% in the same period: Kunkafa’s confidence: 70%
Either, both or neither could happen.
GoldExample↑ Moves up
+1%
forecast move · 12 days
84%
Kunkafa’s confidence in reaching it
Below it, the other side: −0.6% · Kunkafa’s confidence 70% · 12 days
GoldExampleForecast move +1% · 12 days · Kunkafa’s confidence 84%
- changedurationKunkafa’s confidence
- +9%2 years68%
- +5%6 months74%
- +2.5%50 days79%
- +1%12 days84%
- +0.3%1 day81%
- +0.1%1 hour78%
- −0.1%1 hour75%
- −0.2%1 day77%
- −0.6%12 days70%
- −2%50 days73%
- −4%6 months71%
- −7%2 years66%
Measured, not promised
Trained on about 10 billion data points. Tested on about 2 billion it had never seen.
Last day
90%
789,808 evaluated
Last 7 days
85%
11,398,987 evaluated
Last 30 days
85%
13,144,963 evaluated
All time
85%
13,144,963 evaluated
Finished in the forecast direction. Counted, every day, on live markets: how past forecasts turned out, at Kunkafa’s confidence of 90% or higher.
Updated 9 September 2026. Past results do not promise future ones. Up and down both remain possible.
Kunkafa’s confidence 90% or higher 85% finished in the forecast direction 85% reached the level 1,583,398 forecasts
Last day
91%
77,367 evaluated
Last 7 days
93%
475,552 evaluated
Last 30 days
93%
538,642 evaluated
All time
93%
538,642 evaluated
US 500 Index
Finished in the forecast direction, at Kunkafa’s confidence of 90% or higher.
Updated 8 September 2026. Past results do not promise future ones. Up and down both remain possible.
Kunkafa’s confidence 90% or higher 93% finished in the forecast direction 93% reached the level 53,527 forecasts
Last day
95%
98,279 evaluated
Last 7 days
92%
470,051 evaluated
Last 30 days
92%
533,402 evaluated
All time
92%
533,402 evaluated
Nasdaq 100
Finished in the forecast direction, at Kunkafa’s confidence of 90% or higher.
Updated 8 September 2026. Past results do not promise future ones. Up and down both remain possible.
Kunkafa’s confidence 90% or higher 92% finished in the forecast direction 92% reached the level 41,445 forecasts
Last day
92%
71,790 evaluated
Last 7 days
89%
327,820 evaluated
Last 30 days
89%
391,184 evaluated
All time
89%
391,184 evaluated
Gold
Finished in the forecast direction, at Kunkafa’s confidence of 90% or higher.
Updated 8 September 2026. Past results do not promise future ones. Up and down both remain possible.
Kunkafa’s confidence 90% or higher 89% finished in the forecast direction 89% reached the level 37,719 forecasts
Why LLMs Fail at Financial Prediction
ChatGPT, Claude, and Gemini are extraordinary at language. But asking them for stock predictions is like asking a poet to do calculus.
LLMs (ChatGPT, Claude, Gemini)
-
Designed for text, not numbers
Language models process words, not price patterns in tabular data
-
Hallucinate certainty
They give confident-sounding answers even when they have no basis for prediction
-
Trained on articles about markets
Not on actual price data - they've read opinions, not charts
-
Cannot quantify uncertainty
No native probabilistic output - just text that sounds confident
"The stock will go up because of positive momentum..."
Kunkafa
-
Built for numbers, not words
Rows and columns of price history, not articles about it
-
Says how likely, not just which way
Every level carries its probability, and both directions are shown
-
Trained on real price history
About 10 billion data points across stocks, indices, currencies, commodities and crypto
-
Seventy experts, not one
When the experts disagree, the probability drops, and you see that too
"Price rises 0.9%: 61% probability. Price falls 1.6%: 55% probability."
The Kunkafa Approach
Purpose-Built for Uncertain Domains
Markets are noisy and unpredictable. We built AI that embraces it.
Every forecast says how sure it is
A 52% is shown as a 52%, and a near-even split is the honest answer, not a failure to find one.
The Proving Ground
Markets are the ultimate test — noisy, adversarial, and unforgiving. If it works here, it works anywhere.
It's about the right tool for the job. LLMs are extraordinary for language. Kunkafa is purpose-built for tabular prediction.
Plans
Start free. Looking at a forecast costs nothing and moves no counter.
All paid plans include a 7-day free trial
For the curious
Free
- Every market in the catalogue, on the shortest forecast
- Follow up to 5 markets
- One alert, so you can stop watching the screen
- The full record of how past forecasts turned out
For the focused
Starter
7-day free trial
- One market of your choosing, on every forecast duration
- Every other market stays on the shortest forecast
- Follow up to 10 markets
- Up to 5 alerts
For the ambitious
Core
7-day free trial
- Every market, on every forecast duration
- Follow up to 25 markets
- Up to 20 alerts
- Wider evidence, and a home screen shaped around what you follow
For the committed
Pro
7-day free trial
- Everything in Core
- Follow up to 100 markets
- Alerts without a cap
- Automated trading, with limits you set and can pause
Free is where every account starts. No trial that ends.
Guides from Kunkafa
The guides readers use most: how to judge an AI market tool, what a probability means, and how to plan a trade around one.