Scoreboard
AI news forecasts: the full record
Before each session an AI model reads the news and forecasts whether EUR/USD, EUR/CHF and USD/CHF will go up or down. Every forecast is listed here once its window has closed, hits and misses alike, with the reasoning behind it and what actually moved the price. The method has been revised several times; the numbers below combine all versions, and each version is also scored on its own. Background: Can AI predict EUR/USD from the news? 120 forecasts later
Hit rate as forecasts add up
shaded = 95% range · dashed = coin flipEarly on a few forecasts swing the rate wildly; the range narrows as more come in. A range that still includes 50% means the result can't be told apart from guessing.
By pair
bar = hit rate · whiskers = 95% range · dashed = coin flip
By session
EU 08–12 UTC · US 12–21 UTC · Day = 08–21 UTC, used only 5–8 Oct
Misses: how sure the AI is of the reason
after each window the AI explains the move and rates how sure it is of that explanation
- Clear reason 7
- Plausible reason 35
- Unclear 43
Day by day
one cell per forecast · EU first, then US · hover a cell for details hit missVersions and weekly audits
now on v6The forecasting method has a version number, shown on every call below. Every Saturday an AI agent audits the past week: it looks at what went wrong, tests new ideas on years of price history, and has a separate skeptic agent try to break each result. A new version ships only when an idea passes both; most weeks nothing does. Versions are scored separately and never mixed, so a change can't hide in an average. We audit the method; we don't promise it gets better. How the weekly audit works.
| Version | In use | Calls | Right | What changed |
|---|---|---|---|---|
| v6 | 2 Nov – 16 Nov | 63 | 31 (49%) |
Tested 4 ideas; one passed: on US federal holidays the US session is much quieter, so its expected size is scaled down. Direction calls are unchanged. Rejected: a direction-aware edge flag, prices reversing after central-bank decisions, and high currency volatility predicting continuation. |
| v5 | 26 Oct – 30 Oct | 30 | 16 (53%) too few calls to compare |
The first weekly audit, together with six studies run the same week. Version 5 adds an expected size of each session, moves in bonds, stocks, oil and gold as context, and a lower confidence cap on days the Fed chair speaks. One tested idea became a rule: statistical edge flags no longer tilt a call, because the skeptic showed they only echoed each pair's long-run drift. Three ideas were rejected. |
| v4 | 15 Oct – 23 Oct | 42 | 17 (40%) too few calls to compare |
The forecaster reads the day's economic calendar and has to search properly before calling. On two days it had made every call after one stale search, including on a US inflation release day. |
| v3 | 12 Oct – 14 Oct | 18 | 14 (78%) too few calls to compare |
A driver such as bond yields can back a call only through how it moved since the previous close, never through its level alone. |
| v2 | 8 Oct – 9 Oct | 9 | 6 (67%) too few calls to compare |
Each call also gets statistics from 15 years of hourly prices, such as how often the pair rose in this window after a similar move. |
| v1 | 5 Oct – 7 Oct | 9 | 2 (22%) too few calls to compare |
The first version: before each session the AI reads the morning news and calls each pair up or down, with no price statistics. |
Below about 50 calls a version's hit rate is mostly luck: the 95% range is wider than ±14 points, so two versions ten points apart can't be told apart. The numbers are shown so nothing is hidden, not as proof that one version is better.
Change log
| Date | What | Outcome | Details |
|---|---|---|---|
| 15 Nov 2026 | Weekly audit 2026-W46 3 ideas tested · 0 passed |
no new version | Tested 3 ideas; none passed, so the method stays at version 6. Rejected: the reaction to a central-bank statement reversing later in the session, bond-market uncertainty making decision days bigger, and the first hour after a Swiss rate decision setting the afternoon direction. |
| 7 Nov 2026 | Weekly audit 2026-W45 4 ideas tested · 0 passed |
no new version | Tested 4 ideas; none passed, so the method stays at version 6. Rejected: a run of US data surprises setting the dollar's direction, a late move before the European open fading, and Swiss bank deposit data predicting the franc. A volatility idea looked promising but is now checked on new data before it can change any call. |
| 31 Oct 2026 | Weekly audit 2026-W44 4 ideas tested · 1 passed |
v6 shipped | Tested 4 ideas; one passed: on US federal holidays the US session is much quieter, so its expected size is scaled down. Direction calls are unchanged. Rejected: a direction-aware edge flag, prices reversing after central-bank decisions, and high currency volatility predicting continuation. |
| 26 Oct 2026 | Lessons v2 approved by a person |
lessons v2 on | The first lesson was reworded so it no longer depends on statistical edge flags, which stopped tilting calls in version 5. |
| 24 Oct 2026 | Weekly audit 2026-W43 4 ideas tested · 1 passed |
v5 shipped | The first weekly audit, together with six studies run the same week. Version 5 adds an expected size of each session, moves in bonds, stocks, oil and gold as context, and a lower confidence cap on days the Fed chair speaks. One tested idea became a rule: statistical edge flags no longer tilt a call, because the skeptic showed they only echoed each pair's long-run drift. Three ideas were rejected. |
| 22 Oct 2026 | Lessons v1 approved by a person |
lessons v1 on | First lesson switched on: when there is no dated news for the window, the call stays at 50% and says it is a coin flip. |
| 15 Oct 2026 | Method v4 by hand, before the weekly audits |
v4 started | The forecaster reads the day's economic calendar and has to search properly before calling. On two days it had made every call after one stale search, including on a US inflation release day. |
| 12 Oct 2026 | Method v3 by hand, before the weekly audits |
v3 started | A driver such as bond yields can back a call only through how it moved since the previous close, never through its level alone. |
| 8 Oct 2026 | Method v2 by hand, before the weekly audits |
v2 started | Each call also gets statistics from 15 years of hourly prices, such as how often the pair rose in this window after a similar move. |
| 5 Oct 2026 | Method v1 by hand, before the weekly audits |
v1 started | The first version: before each session the AI reads the morning news and calls each pair up or down, with no price statistics. |
Locked in — window not closed yet
6 forecastsThese forecasts are already made, but you can't see them yet - only each one's hash: a 64-character code computed from the forecast and a random secret. Change one letter of the forecast and the hash comes out completely different, so we can't swap a forecast after the price moves. Copy a hash now and compare it after the result. How to check.
a2ed6ee54f7670f3615b80a6dc2b184a7c53b02933834c69848da16f7a61144a
.ots proof
sealed 11:17 UTC · OpenTimestamps: submitted 17 Nov 11:17 UTCdc71df323eb6e5ebb77c81841fe647c610475a643bfc912542358751f748efa1
.ots proof
sealed 11:17 UTC · OpenTimestamps: submitted 17 Nov 11:17 UTCc7e2e94762ef5591274dfcaa776ce5ac9616ae7c99823593d137aab821d21338
.ots proof
sealed 11:17 UTC · OpenTimestamps: submitted 17 Nov 11:17 UTCebe94c226f20fadf8bf8f80c1f2b89900a430c27243eb2284ea3fdc27968c7bb
.ots proof
sealed 07:37 UTC · OpenTimestamps: submitted 17 Nov 07:37 UTCe8f568706266f88464e22942aae49acf7a73c1a8f471c8506c2d7ae4ab181d04
.ots proof
sealed 07:37 UTC · OpenTimestamps: submitted 17 Nov 07:37 UTC1b8b6fcf7d748f52c0cd7d96b6df310eb9218dd580c0a4a796d76b96779e4156
.ots proof
sealed 07:37 UTC · OpenTimestamps: submitted 17 Nov 07:37 UTCEvery forecast
171 forecasts
"Why it moved" is written by the AI after the window closed, from the day's news. It can be wrong, and it says so: clear, plausible or unclear is its own confidence in the explanation. Moves are in pips from the window's open.
Model's technical note
Euro near 20-day lows with firm dollar backdrop; no fresh news found for today; driver: dollar/yield backdrop unverified since 21:00 so confidence kept near 50; no lessons active; stats: pre-window +0.04 ATR; prev day -0.15 ATR; EDGE continue (LB 51.4 vs 49.8) - tilted downModel's technical note
Dollar resilient and franc pressured by zero SNB rates; no fresh news found; driver: rate spread unchanged since 21:00 (supports up) - low confidence; no lessons active; stats: pre-window +0.13 ATR EDGE continue (LB 51.4 vs 50.4) and prev day -0.30 ATR EDGE reverse (LB 51.9 vs 50.9) both point up - tilted upModel's technical note
Franc bid versus soft euro and no EZ/CH catalysts; stats: pre-window +0.03 ATR reverse EDGE (LB 51.9 vs 49.1) and prev day -0.13 ATR continue EDGE (LB 52.9 vs 51.7) both point down - tilted downModel's technical note
Firm dollar and yields with euro at multi-month lows; only UoM sentiment at 14:00 so thin catalyst; no lessons active; stats: pre-window +0.11 ATR; no edgeModel's technical note
SNB at zero with franc under pressure and firm US yields; thin calendar; no lessons active; stats: pre-window -0.11 ATR; no edgeModel's technical note
French fiscal premium vs bid franc keeps slight downside lean; no fresh catalyst found; stats: pre-window +0.15 ATR; no edgeModel's technical note
Euro under pressure from high US yields and euro-zone fiscal risk; thin fresh news so small lean; stats: pre-window +0.24 ATR; EDGE reverse (LB 51.5 vs 49.9) - tilted downModel's technical note
Hawkish Fed repricing and firm yields support dollar; thin news; stats: pre-window -0.12 ATR and prev day -0.27 ATR; EDGE reverse (LB 52.2 vs 50.0) - tilted upModel's technical note
French risk premium weighs on euro while franc stays bid; stats: overnight +0.03 ATR; EDGE reverse (LB 53.0 vs 48.6 baseline) - tilted downModel's technical note
Fed re-tightening and French budget stress keep euro on the back foot with yields at multi-year highs; quiet overnight so leaves room; stats: overnight -0.03 ATR; no edgeModel's technical note
Dollar supported by hawkish Fed repricing and high Treasury yields; Commerzbank sees franc weakness through 2026 but pair near 20-day high; stats: 3-day up streak; no edgeModel's technical note
French risk premium weighs on euro while franc safe-haven bid persists; slight lean as bounce could extendModel's technical note
Euro bounced Tuesday but French fiscal stress persists and hawkish FOMC minutes with Fed speakers may revive dollar bids; light data calendarModel's technical note
Hawkish FOMC minutes and Fed speakers could lift the dollar after a dip but franc safe-haven demand caps gains; near coin flipModel's technical note
Euro weakness from French debt concerns plus safe-haven franc support with SNB floor at 0%; neutral intraday bias caps convictionModel's technical note
Euro near 17-month low ~1.122 on French fiscal stress and rising US yields; momentum persists and Eurozone retail sales are unlikely to reverse itModel's technical note
Dollar rides higher Treasury yields but rallies are capped below 0.8320 with franc safe-haven bid; near coin flip with slight dollar-momentum leanModel's technical note
French debt stress drove a record one-day drop to ~0.928 and safe-haven CHF demand with a 0% SNB floor should persistModel's technical note
Four straight weekly losses and deeply oversold near 1.1250 support with a quiet Monday calendar favour a modest bounce; Friday payrolls and Fed hike risk cap itModel's technical note
Dollar overextended after three weekly gains and franc safe-haven bid on euro-area stress; rising US yields limit downsideCheck a forecast yourself — 3 steps
A hash is a fingerprint of a text: the same text always gives the same 64 characters, and changing a single letter gives a completely different one. So if the hash you saw before the window matches the forecast shown after it, the forecast was not changed.
7b147f2ee27226a91593d4cf033e0524…fx2owl-fx-v1|2026-11-09|eu|EURUSD|up|55|secret✓ MatchesForecasts made before 9 Nov 2026 have no hash. The secret at the end of the line is random and shown only after the result - without it nobody could check the hash, and with it anyone can.
When was the hash made? Check it on opentimestamps.org
Each hash is also sent to OpenTimestamps, a free public service that writes it into the Bitcoin blockchain within a few hours. Nobody - us included - can change a Bitcoin block afterwards, so this proves the forecast was not rewritten after that block.
- Open the forecast's "Sealed before the window" and download two files: Download as .txt (the line) and Download the timestamp proof (.ots).
- Go to opentimestamps.org. In "Stamp & Verify", drop the
.otsfile. - When it asks for the stamped file, drop the
.txtfile. It is hashed in your browser, not uploaded. - It shows the Bitcoin block and its date - the hash existed by then. In the first few hours after sealing it shows the proof as pending: try again later.
The "sealed" time next to each forecast is when our server received the hash; the block's date is independent of us but comes later, usually one to a few hours after sealing.
For developers: the command line
The hashed line is fx2owl-fx-v1|date|session|PAIR|call|confidence|salt, UTF-8, no newline
at the end. The salt is 32 random hex characters, kept secret until the window is scored, so the hash
can't be guessed from the few possible forecasts. To hash a line yourself:
printf '%s' 'fx2owl-fx-v1|2026-11-06|eu|EURUSD|up|55|00112233445566778899aabbccddeeff' | sha256sum
(on macOS use shasum -a 256). On Windows PowerShell:
$t = 'fx2owl-fx-v1|2026-11-06|eu|EURUSD|up|55|00112233445566778899aabbccddeeff'
-join ([Security.Cryptography.SHA256]::Create().ComputeHash([Text.Encoding]::UTF8.GetBytes($t)) | ForEach-Object { $_.ToString('x2') })
The output must equal the published hash. With the
OpenTimestamps client,
put the downloaded .txt and .ots in one folder (their names already match) and run
ots verify fx2owl-<hash>.txt.ots; ots upgrade on the same file saves the
completed proof. The client verifies against your own Bitcoin Core node (a pruned one is fine).
Updated 17 Nov 2026 12:07 UTC. Source links go only to independent news sites and official sources (central banks, statistics offices). Educational content, not financial advice. Past results don't guarantee future ones.