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
57 out of 171 shown
"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
coin flip; no dated driver; EZ flash PMI 08:00 already out and US data 13:45 flash PMI in window with no consensus found; driver: none confirmed since 21:00; L1 applies (no driver; no EDGE) - 50; stats: pre-window -0.22 ATR; no statistical edge; no dated news: 8 searches returned only stale pages; snippets only - fetches blockedModel's technical note
France debt worries weigh on euro and USD regained ground late Oct 22 (fxstreet snippet); EZ flash PMI 08:00 cons 52.8 in window; driver: US 10Y fell ~16bp below 5% since 21:00 (against down) but DXY only near 3wk low and France fiscal risk offsets - kept down small; L1 applies (partial dated driver); stats: prev day -0.23 ATR; EDGE continue (LB 51.5 vs 49.8) - tilted down; snippets only - fetches blockedModel's technical note
DXY slipped from 102.07 to ~101.5 and US 10Y retraced from 5.14% as Oct hike odds fell to ~17%; jobless claims 12:30 cons 200K in window; snippets only - fetches blocked; L1 n/a (dated driver); driver: US yields falling since 21:00 (supports up) - 54; stats: pre-window -0.15 ATR; no edgeModel's technical note
driver: DXY ~101.5 and lower since 21:00 on Fed-pause bets (supports up); French OAT 5% and Moody's review Oct 23 cap upside; stats: pre-window +0.18 ATR; EDGE reverse (LB 51.7) vs prev-day EDGE continue - offset; snippets only; no lessons activeModel's technical note
No lesson active; no dated Oct 21 news found (6 searches; fetches not tried after search snippets stale; snippets only); no release in events.csv for window; ECB hawkish backdrop (deposit 2.50%; HICP 3.8%) and Fed Oct 27-28 ahead not in window; driver: none verifiable since 21:00 UTC - 51 on stats only; stats: pre-window -0.23 ATR; no edgeModel's technical note
No lesson active; no dated Oct 21 news found (6 searches; fetches not available; snippets only); no EU/CH release in events.csv; Fed meets Oct 27-28 so event risk is ahead not in window; driver: none verifiable since 21:00 UTC - 52 on stats only; stats: pre-window -0.22 ATR; EDGE continue (LB 50.2 vs 49.8) - tilted downModel's technical note
No lesson active; no US release in events.csv and no dated Oct 20 calendar found (11 searches; fetches blocked; snippets only - no Oct 20 news found); driver: US 10Y ~5.1% on oil near $95-99 and French risk weigh on euro but direction since 21:00 close unverified - 51; stats: pre-window +0.04 ATR; no statistical edgeModel's technical note
No lesson active; no EU release in events.csv and no dated calendar found (snippets only - fetches blocked; 5 searches); driver: US 10Y rebounded to ~5.13-5.14% on oil >$99 after Monday's lull and 171bp spread to Bund (supports down); stats: pre-window +0.22 ATR; EDGE reverse (LB 51.6 vs 49.8) - tilted downModel's technical note
No lesson active; no US release found in window (events.csv empty; calendar not confirmed - snippets only - fetches blocked; 6 searches); driver: Fed Oct 28 hike odds fading (~12-30%) and USD/yields lower since Friday close (supports up) but euro fell 31 pips this morning - 51; stats: pre-window -0.41 ATR; no edgeModel's technical note
Snippets only - fetches blocked; 6 searches; Fed hold odds ~84% for Oct 27-28 and dollar near 2-week low as US yields fell since Friday's close; French riots hit the euro at the open but it recovered most of the gap; no EU-window release found in events.csv; driver: US yields down since 21:00 Fri (supports up) - 51; stats: pre-window -0.14 ATR; EDGE continue (LB 50.2) ignored as marginalModel's technical note
Snippets only - fetches blocked and 6 searches found no dated 16 Oct wrap; the Fed hike odds cut and US 10Y -9bp since 21:00 after hot PPI 1.3% and retail sales 0.8% keep the dollar soft; in window US import prices 12:30 and industrial production 13:15 with no consensus found so confidence low; no Active lessons; driver: US 10Y -9bp since 21:00 supports up - 51; stats: pre-window +0.48 ATR and prev day +0.85 ATR; no edgeModel's technical note
Dollar softer as US 10Y fell ~9bp after hot Sep PPI 1.3% m/m and retail sales 0.8% cut Oct Fed hike odds (DXY heading for weekly drop; Warsh no signal; FOMC 27-28 Oct) and no EZ/CH release found in window; driver: US 10Y -9bp since 21:00 supports up; stats: pre-window +0.21 ATR and prev day +0.85 ATR; EDGE reverse (LB 51.7 vs 49.8) - tilted confidence down to 51Model's technical note
US PPI m/m 12:30 cons 0.5% and retail sales 12:30 in window (surprise unknown so low confidence); hot Sep CPI kept Fed-hike pricing but EURUSD bounced +61 pips (+0.87 ATR) pre-window so the dollar driver moved against a down call since 21:00 and only the reversal tilt remains - 51; searches for 15 Oct news returned only stale pages and fetches failed; stats: pre-window +0.87 ATR; no edgeModel's technical note
Hot US Sep CPI (3.7% y/y; core 0.3% m/m vs 0.2%) lifted Fed-hike bets and sent EURUSD to 1.1113 lowest since May 2025 on 14 Oct but the dollar faded late and the pair is +52 pips (+0.74 ATR) pre-window so the driver (Fed-hike repricing) moved against the call since 21:00 - 51; no EU-window release in events.csv (US PPI/retail 12:30 is after close); stats: pre-window +0.74 ATR; no edgeModel's technical note
No dated 14 Oct news found in search; European morning flat (-0.07 ATR) at 10% of 20-day range; driver: none verified since 21:00 - 50; stats: pre-window -0.07 ATR; no edgeModel's technical note
No dated 14 Oct news found in search; small +0.15 ATR pre-window bounce at 14% of 20-day range; driver: none verified since 21:00 (no news edge) - 51; stats: pre-window +0.15 ATR; prev day +0.66 ATR; EDGE reverse (LB 51.6 vs 49.8) - tilted downModel's technical note
No dated 13 Oct news found; early-Oct dollar strength on record-high US yields and euro energy/fiscal worries persist but pre-window +0.38 ATR bounce is already in; driver: US yields level unverified since 21:00 so confidence kept near 50; stats: pre-window +0.38 ATR; no edgeModel's technical note
No fresh overnight or EU-calendar news found; weak euro trend with 2-day down streak and price at 6% of 20-day range; driver: dollar/yield backdrop unverified since 21:00 so no news support; L none active; stats: pre-window +0.35 ATR no edge; prev day -0.46 ATR EDGE continue (LB 51.4 vs 49.8) - tilted downModel's technical note
Euro weak after morning slide with firm dollar tone and no fresh US-window news found; driver: dollar/yield backdrop unverified since 21:00 so confidence kept near 50; no lessons active; stats: pre-window -0.28 ATR; no edgeModel'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
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
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
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
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
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
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 itCheck 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 11:34 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.