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

AI news forecasts · EUR/USD, EUR/CHF, USD/CHF
coin 50%
50.3%
hit rate · 86 of 171 forecasts · all method versions
50.3%AI
50%coin flip
43%–58%95% range
95% range: the true hit rate is very likely inside it
Can't be told apart from guessing — yet

Hit rate as forecasts add up

shaded = 95% range · dashed = coin flip
5 Oct · forecast 1 16 Nov · forecast 171

Early 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

EUR/CHF 51%
EUR/USD 54%
USD/CHF 46%

By session

EU 08–12 UTC · US 12–21 UTC · Day = 08–21 UTC, used only 5–8 Oct

US 51%
EU 54%
Day 25%

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: 7Plausible reason: 35Unclear: 4385misses
  • 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 miss
5 Oct
6 Oct
7 Oct
8 Oct
9 Oct
12 Oct
13 Oct
14 Oct
15 Oct
16 Oct
19 Oct
20 Oct
21 Oct
22 Oct
23 Oct
26 Oct
27 Oct
28 Oct
29 Oct
30 Oct
2 Nov
3 Nov
4 Nov
5 Nov
6 Nov
9 Nov
10 Nov
11 Nov
12 Nov
13 Nov
16 Nov

Versions and weekly audits

now on v6

The 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.

VersionIn useCallsRightWhat 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

DateWhatOutcomeDetails
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 forecasts

These 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.

Tue 17 Nov · US · EUR/CHF a2ed6ee54f7670f3615b80a6dc2b184a7c53b02933834c69848da16f7a61144a .ots proof sealed 11:17 UTC · OpenTimestamps: submitted 17 Nov 11:17 UTC
Tue 17 Nov · US · EUR/USD dc71df323eb6e5ebb77c81841fe647c610475a643bfc912542358751f748efa1 .ots proof sealed 11:17 UTC · OpenTimestamps: submitted 17 Nov 11:17 UTC
Tue 17 Nov · US · USD/CHF c7e2e94762ef5591274dfcaa776ce5ac9616ae7c99823593d137aab821d21338 .ots proof sealed 11:17 UTC · OpenTimestamps: submitted 17 Nov 11:17 UTC
Tue 17 Nov · EU · EUR/CHF ebe94c226f20fadf8bf8f80c1f2b89900a430c27243eb2284ea3fdc27968c7bb .ots proof sealed 07:37 UTC · OpenTimestamps: submitted 17 Nov 07:37 UTC
Tue 17 Nov · EU · EUR/USD e8f568706266f88464e22942aae49acf7a73c1a8f471c8506c2d7ae4ab181d04 .ots proof sealed 07:37 UTC · OpenTimestamps: submitted 17 Nov 07:37 UTC
Tue 17 Nov · EU · USD/CHF 1b8b6fcf7d748f52c0cd7d96b6df310eb9218dd580c0a4a796d76b96779e4156 .ots proof sealed 07:37 UTC · OpenTimestamps: submitted 17 Nov 07:37 UTC

26 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.

Mon 16 Nov
US session · written 11:17 UTC · v6
EUR/USD
▲ Up 50% sure
✗ Miss
-13.3 pips
max up +10.4 · max down -18.5
Sealed before the window
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-16|us|EURUSD|up|50|1f7748163f3613b2374c145082ca0240
2. Its hash, published before the window
e478fa474e9bce24220285b0f434424794824a71f5c0814ee8129c6b3982af83
sealed 11:17 UTC · OpenTimestamps: submitted 16 Nov 11:17 UTC
Download the timestamp proof (.ots)
Why this forecast
The dollar is near a 19-month high on bets for a Fed rate hike, but US yields have slipped since Friday and Fed chair Warsh speaks late in the session. There is no clear direction, so this is close to a coin flip.
Model's technical note Warsh speaks 17:00 in window (Fed chair cap 55); dollar at 19-month high on Dec hike bets but driver: US 2y -1.8bp and 10y -1.1bp since 21:00 are against a dollar-up call - 50; coin: up; L1 applies (kept at 50); stats: pre-window -0.18 ATR; no edge; no cross-asset gap; snippets only - fetches partly blocked
Why it moved plausible
Euro slid to a 19-month low under 1.1000 as Fed hike bets and risk-off (US-Iran tension; weak 13:30 Empire State) kept the dollar bid and the pair sagged through the Warsh talk at 17:00; Lagarde speaking made no difference
Fri 13 Nov
EU session · v6
EUR/USD
▲ Up 50% sure
✗ Miss
-5.6 pips
max up +9.4 · max down -12.7
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-13|eu|EURUSD|up|50|90b2ccd5281cae035efe68c99429f11d
2. Its hash, published before the window
851ab3c872b56237941740056caff097aaf90ed1754549e1a7f80616382a6003
sealed 17:51 UTC · OpenTimestamps: submitted 13 Nov 17:51 UTC
This hash arrived after the window opened, so it proves nothing about foresight.
Download the timestamp proof (.ots)
Why this forecast
Nothing new is due for the euro this morning and the dollar's strength from rate-hike bets has paused. This is close to a coin flip.
Model's technical note Dollar index above 103 after three gains on Fed hike bets (Waller 50bp Dec; Dec hike ~85% priced) but driver: US 2y -1.6bp and 10y -0.2bp since 21:00 (against a dollar-up call) with no dated EUR driver - 50; coin: up; L1 applies (kept 50); PPI 13:30 is after the window; stats: pre-window +0.03 ATR; EDGE reverse/continue conflicting - not used
Why it moved unclear
Drifted lower into 10:00 with no dated EUR or USD release in the window; no clear driver
Thu 12 Nov
EU session · v6
EUR/USD
▼ Down 54% sure
✗ Miss
+7.2 pips
max up +17.5 · max down -0.5
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-12|eu|EURUSD|down|54|a853d8c324c83f5e4f32610507ff8d84
2. Its hash, published before the window
857e61cf457b668e49079c3cb11e947c01dee0839df9028dddecf88c17d97685
sealed 17:51 UTC · OpenTimestamps: submitted 13 Nov 17:51 UTC
This hash arrived after the window opened, so it proves nothing about foresight.
Download the timestamp proof (.ots)
Why this forecast
The dollar is at its strongest in over a year as inflation came in hot and Fed officials talk about more rate hikes, which should keep weighing on the euro. A calmer dollar would flip this.
Model's technical note Dollar index near 103 at highest since Apr 2025 after hot October CPI and hawkish Fed (Waller 50bp Dec; Logan); driver: Fed hike pricing ~91% with US 10y +0.7bp since 21:00 (with down) - mild; no EZ/CH data in window; snippets only - fetches partly blocked; L1 n/a; stats: pre-window -0.2 ATR; EDGE continue - not used
Why it moved plausible
Euro edged up in a quiet European morning as the dollar paused after its run to a multi-month high; no dated EZ or US release inside the window
Tue 10 Nov
EU session · v6
EUR/USD
▲ Up 50% sure
✗ Miss
-24.2 pips
max up +10.0 · max down -27.4
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-10|eu|EURUSD|up|50|d17992b974563aff5200afb00d13e832
2. Its hash, published before the window
645f4b532d8be14929dd0d1150be2212299ae67c7dec9ffee35e5a5bf0edc69a
sealed 17:51 UTC · OpenTimestamps: submitted 13 Nov 18:01 UTC
This hash arrived after the window opened, so it proves nothing about foresight.
Download the timestamp proof (.ots)
Why this forecast
No euro-area news is due this morning and the big US inflation report only comes in the afternoon, so this is close to a coin flip.
Model's technical note L1 applies (no EU-window driver; US CPI 13:30 is outside the window; snippets only - fetches partly blocked); driver: US 2y -0.4bp and 10y -0.2bp since 21:00 flat (not against); coin: up; stats: pre-window +0.10 ATR; prev day +1.26 ATR; EDGE reverse - not used
Why it moved plausible
Euro faded after a brief 08:00 pop as the dollar was bid into US CPI after Waller put a 50bp December hike in play; no dated release inside the window
Mon 9 Nov
US session · v6
EUR/USD
▼ Down 50% sure
✗ Miss
+32.5 pips
max up +35.7 · max down -3.6
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-09|us|EURUSD|down|50|c28c5df90ddef13add3d3933c287451e
2. Its hash, published before the window
2b565a563a490e0ebf2f5e429958df62d8218ce0e9b73ff42384566c07474c8e
sealed 17:51 UTC · OpenTimestamps: submitted 13 Nov 18:08 UTC
This hash arrived after the window opened, so it proves nothing about foresight.
Download the timestamp proof (.ots)
Why this forecast
No major US data is due today and the big inflation report comes tomorrow, so there is no clear push either way. This is close to a coin flip.
Model's technical note L1 applies (no clear dated driver for the window; US 2y +0.8bp and 10y -0.2bp since 21:00 flat; only Fed speakers Bowman 13:40 Goolsbee 15:00 in window; US CPI tomorrow); coin: down; stats: pre-window +0.79 ATR; no edge; fetches partial
Why it moved plausible
Dollar sold off through the session with a late leg higher around 19:00 UTC as stocks hit highs on Iran deal headlines; Fed speakers Barkin and Goolsbee gave no hawkish surprise
Thu 5 Nov
US session · v6
EUR/USD
▲ Up 52% sure
✗ Miss
-2.6 pips
max up +22.4 · max down -18.6
Why this forecast
The dollar looks slightly soft as markets expect a Democratic Congress to limit government spending and keep US bond yields in check. US jobless claims at 13:30 UTC could shake this up, so it is only a slight lean higher.
Model's technical note BoE decision ~12:00 and US claims 13:30 cons 196K in window; Democratic Congress seen limiting fiscal expansion and USD upside (snippets only); driver: US 10y -0.7bp since 21:00 (with up; tiny) - 52; r20 S&P -0.32 not contradicted; no Fed chair event; stats: pre-window +0.02 ATR; no edge
Why it moved unclear
Euro-dollar dipped after the 13:30 claims then rallied to 17:00 and faded to flat; no clear driver (midterm and BoE context only)
Thu 5 Nov
EU session · v6
EUR/USD
▲ Up 50% sure
✗ Miss
-20.8 pips
max up +6.7 · max down -26.0
Why this forecast
No important eurozone or Swiss news is due this morning and the dollar's moves around the US midterms are already priced in, so this is close to a coin flip with a slight lean to the euro.
Model's technical note L1 applies (no dated EU-morning driver; snippets only - fetches blocked); coin: up; BoE decision ~12:00 at window close; driver: S&P fut -0.16% since 21:00 (r20 -0.32 weak; with up) - 50; no cross-asset edge; stats: pre-window +0.57 ATR at 95% of 20d range; no edge
Why it moved unclear
Euro-dollar drifted lower through the window ahead of the 12:00 BoE decision; no dated catalyst found
Tue 3 Nov
EU session · v6
EUR/USD
▲ Up 52% sure
✗ Miss
-17.0 pips
max up +7.7 · max down -22.6
Why this forecast
Stock futures fell as US-Iran talks stalled and oil jumped, a mood that has tended to help the euro against the dollar lately. A small lean up.
Model's technical note driver: S&P fut -0.34% since 21:00 as US-Iran deal stalls and Brent +2.65% (r20 -0.53 with up) while US 10y +0.9bp flat; L1 does not apply (dated driver); stats: pre-window -0.04 ATR; EDGE not used; fetches via investinglive/tradingeconomics
Why it moved unclear
Euro sold steadily through the morning with no dated release in the window; no clear driver
Mon 2 Nov
US session · v6
EUR/USD
▲ Up 52% sure
✗ Miss
-13.6 pips
max up +22.6 · max down -17.0
Why this forecast
Oil fell sharply on hopes of a US-Iran deal over the Strait of Hormuz and stocks rose, softening the dollar. The euro had already gained in the morning. A small lean up.
Model's technical note driver: Brent -4.5% since 21:00 on US-Iran Hormuz deal hopes and S&P +0.5% (r20 -0.52 with up) while US 10y -0.9bp flat; dollar softer; US ISM Mfg 15:00 cons 54.7 in window; pre-window +1.0 ATR already partly priced; L1 n/a; stats: pre-window +1.00 ATR; no edge; snippets plus partial fetches
Why it moved clear
Euro rose to 13:00 then reversed when ISM Manufacturing 55.5 beat 54.6 consensus at 15:00 (-16 pips in the hour) and the pair kept sliding into the close
Fri 30 Oct
US session · v5
EUR/USD
▲ Up 52% sure
✗ Miss
-40.6 pips
max up +1.0 · max down -59.4
Why this forecast
US interest rates fell overnight, which tends to help the euro. US wage-cost data and a business survey were due. A small lean up.
Model's technical note driver: US 10Y -2.9bp since 21:00 (with up; r20 -0.25); US ECI 12:30 and Chicago PMI 13:45 in window; EZ Q3 GDP beat but sticky EZ inflation; gold -1.1% against; L1 n/a; stats: pre-window +0.31 ATR; no edge
Why it moved clear
Euro dropped ~25 pips at 13:00 on soft German prelim CPI (-0.2% m/m vs +0.1% expected; 2.8% y/y) which cut ECB-hike bets and the dollar then held the gain after Chicago PMI
Thu 29 Oct
US session · v5
EUR/USD
▼ Down 50% sure
✗ Miss
+37.2 pips
max up +43.5 · max down -37.8
Why this forecast
The ECB decision and US growth data were due in the window, but no clear driver was found. A coin flip.
Model's technical note ECB 13:15 UTC hold expected and US Q3 GDP/claims 12:30 in window; L1 applies (no dated pair driver; snippets only - fetches blocked; 6 searches); coin flip; driver: US 2y -0.8bp since 21:00 (flat - no support); stats: pre-window -0.31 ATR; no edge
Why it moved plausible
Dollar firmer on 12:30 US GDP beat (3.4% vs 3.2%) and low claims (194K) pushing EURUSD to -38; euro then reversed after the 13:15 ECB hold with talk of a December hike and rose steadily; extra late rise from 20:00 unexplained
Thu 29 Oct
EU session · v5
EUR/USD
▲ Up 51% sure
✗ Miss
-2.1 pips
max up +7.9 · max down -18.8
Why this forecast
The Fed held rates and expectations for a December rise barely moved. The big data came after the session, so this was close to a coin flip with a slight lean up.
Model's technical note Fed held on Warsh with Dec hike bets barely moved (investinglive snippets only; tradingeconomics fetch blocked); ECB 13:15 and US GDP/claims 12:30 fall after the 12:00 close so no in-window release; L1 applies (no pair-specific driver) so kept near coin flip; driver: US 2y -1.4bp since 21:00 (with up; beta -2.1 pips/bp) - 51; stats: pre-window -0.24 ATR; EDGE continue not used
Why it moved unclear
Choppy range with no scheduled release before the 12:00 close; euro dipped to 09:00 then recovered to flat; no clear driver
Wed 28 Oct
US session · v5
EUR/USD
▼ Down 53% sure
✗ Miss
+22.4 pips
max up +39.2 · max down -7.7
Why this forecast
The Fed was expected to hold rates with a tough tone, and the euro was weak on French bond worries. Confidence was capped because the Fed press conference fell inside the window.
Model's technical note FOMC 18:00 UTC hold expected (hawkish; Warsh press conf in window so confidence capped at 55) while euro is weak on French bond stress and fiscal worries; driver: US 2y +1bp since 21:00 (with down; r20 -0.29); snippets and investinglive only - tradingeconomics fetch blocked; stats: pre-window +0.04 ATR; no edge
Why it moved plausible
Euro climbed from 15:00 and spiked at the 18:00 FOMC decision then held +20 pips as the dollar sold off on the Fed outcome/press conference; exact message not confirmed in sources
Wed 28 Oct
EU session · v5
EUR/USD
▼ Down 52% sure
✗ Miss
+7.9 pips
max up +9.1 · max down -2.4
Why this forecast
German consumer confidence fell and markets were waiting for the Fed decision later that day. Short-term US rates edged up. A small lean down.
Model's technical note snippets only - tradingeconomics blocked; GfK fell to -30.8 and markets sit pre-FOMC (18:00 outside window); driver: US 2y +1.8bp since 21:00 (with down; r20 -0.29 weak); L1 n/a; stats: pre-window -0.15 ATR; EDGE continue not used
Why it moved unclear
Euro drifted higher through a quiet pre-FOMC morning with no dated release in the window; small gains held into 12:00
Fri 23 Oct
US session · v4
EUR/USD
▼ Down 50% sure
✗ Miss
+11.2 pips
max up +21.6 · max down -2.0
Why this forecast
No news drove the pair; the euro-area survey was already out and the US survey had no forecast. A coin flip.
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 blocked
Why it moved unclear
Euro rebounded from 12:00 after a -25 pip pre-window drop and held the gain with a late lift at 20:00; no dated driver found
Thu 22 Oct
EU session · v4
EUR/USD
▲ Up 52% sure
✗ Miss
-36.1 pips
max up +9.2 · max down -42.0
Why this forecast
The dollar slipped overnight on bets the Fed would pause. French debt worries and a credit-rating review the next day limited the euro's upside. A small lean up.
Model'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 active
Why it moved plausible
Euro sagged through the morning as French 10y yields held above 5% ahead of the Moody's review on Oct 23; the Asia dollar slide did not extend
Wed 21 Oct
US session · v4
EUR/USD
▼ Down 51% sure
✗ Miss
+1.9 pips
max up +11.5 · max down -14.8
Why this forecast
No news for the day was found and no data was due. The ECB sounded tough but the Fed meeting was still ahead. A weak lean down based on history.
Model'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 edge
Why it moved unclear
Choppy range with a dip to -15 pips at 15:00 and a rebound by 17:00; dollar slipped in a quiet session with no scheduled release
Wed 21 Oct
EU session · v4
EUR/USD
▼ Down 52% sure
✗ Miss
+3.7 pips
max up +8.2 · max down -11.8
Why this forecast
No news for the day was found and no data was due; the Fed meeting was still a week away. The call relied on history alone, which leaned slightly lower.
Model'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 down
Why it moved unclear
Dipped about 12 pips by 09:00 then recovered with a 10:00 spike; no dated release or headline found for the window
Tue 20 Oct
US session · v4
EUR/USD
▼ Down 51% sure
✗ Miss
+25.8 pips
max up +49.6 · max down -0.4
Why this forecast
No news for the day was found. High US interest rates, expensive oil and French worries weighed on the euro, but nothing confirmed the direction. A weak lean down.
Model'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 edge
Why it moved clear
Reports of US-Iran deal progress cut oil and yields around 14:00 UTC and the dollar fell broadly
Mon 19 Oct
US session · v4
EUR/USD
▲ Up 51% sure
✗ Miss
-17.2 pips
max up +0.1 · max down -26.2
Why this forecast
Fading bets on a US rate rise and lower US interest rates since Friday supported the euro, though it fell in the morning. A weak lean up.
Model'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 edge
Why it moved unclear
Dollar bid from 14:00 to 16:00 UTC reversed the morning euro gain with yields firming; no scheduled release found and no dated trigger
Fri 16 Oct
US session · v4
EUR/USD
▲ Up 51% sure
✗ Miss
-18.8 pips
max up +4.7 · max down -44.3
Why this forecast
Little fresh news was found. Lower odds of a US rate rise and falling US interest rates kept the dollar soft. Only minor US data was due, so confidence was low.
Model'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 edge
Why it moved plausible
Dollar rebounded sharply 15:00-16:00 UTC (EURUSD -37 pips) amid AI-stock selloff and credit stress risk-off before Warsh's no-prejudge remarks; euro only partly recovered into the close
Thu 15 Oct
US session · v4
EUR/USD
▼ Down 51% sure
✗ Miss
+11.6 pips
max up +17.3 · max down -18.7
Why this forecast
US producer prices and retail sales were due in the afternoon, with an unknown outcome. The euro had already bounced strongly in the morning, so only a weak lean that it pulls back.
Model'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 edge
Why it moved clear
Hot US PPI (1.3% m/m vs 0.5% expected) and strong retail sales failed to revive Fed hike bets (Oct odds fell to about 26%) so the dollar weakened and EURUSD rose into the close
Tue 13 Oct
US session · v3
EUR/USD
▼ Down 51% sure
✗ Miss
+10.9 pips
max up +17.2 · max down -2.4
Why this forecast
No news for the day was found. The dollar had been strong on record-high US interest rates and euro worries, but the euro had already bounced in the morning. Kept close to a coin flip.
Model'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 edge
Why it moved plausible
Dollar retreated from recent highs and the euro rose through the session; softer-dollar tone before US CPI with dovish Fed rhetoric late in the day (peak at 18:00); French fiscal risk still limited gains
Thu 8 Oct
Day session · v2
EUR/USD
▼ Down 52% sure
✗ Miss
+14.3 pips
max up +31.6 · max down -23.4
Why this forecast
Talk of further US rate rises and French budget worries kept the euro on the back foot, with US interest rates at multi-year highs. Nothing much happened overnight.
Model'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 edge
Why it moved plausible
Euro slid to -23 pips by 11:00 on French fiscal worries then reversed in the US session as Treasury yields retreated after sub-200K jobless claims (197K) and Fed minutes; closed above the open
Wed 7 Oct
Day session · v1
EUR/USD
▼ Down 52% sure
✗ Miss
+5.9 pips
max up +13.8 · max down -25.3
Why this forecast
The euro bounced the day before, but French debt worries remained, and the Fed's meeting notes and speakers could support the dollar again. Not much data was due.
Model's technical note Euro bounced Tuesday but French fiscal stress persists and hawkish FOMC minutes with Fed speakers may revive dollar bids; light data calendar
Why it moved plausible
French fiscal stress sent the euro down in the 07:00 hour (1.1228 to 1.1190) before the window; inside it the pair dipped to ~1.1165 by 12:00 then recovered to the open as the French risk premium stopped widening and the Fed minutes were not a shock
Tue 6 Oct
Day session · v1
EUR/USD
▼ Down 54% sure
✗ Miss
+17.9 pips
max up +36.2 · max down -14.5
Why this forecast
The euro was near a 17-month low on French debt worries and rising US interest rates. That pressure looked likely to continue, and the day's euro-area data seemed unlikely to change it.
Model'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 it
Why it moved plausible
OAT-Bund spread narrowed ~16bp to ~127bp and French 10y yields fell ~11bp; the euro jumped from ~07:00 and kept rising

Check 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.

1 Before the window: copy the hash "Locked in" at the top of this page lists each upcoming forecast with only its hash. Press "Copy hash" and keep it (a note, a screenshot). 7b147f2ee27226a91593d4cf033e0524…
2 After the result: open the forecast Results arrive after the evening analysis (about 22:30 UTC). Find the forecast under "Every forecast" and click "Sealed before the window" under its result. It shows the forecast written as one line. fx2owl-fx-v1|2026-11-09|eu|EURUSD|up|55|secret
3 Check that they match Press "Check: hash the line in my browser" (nothing is sent to us), or paste the line into any SHA-256 tool. The result must be the hash you copied in step 1. ✓ Matches

Forecasts 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.

  1. Open the forecast's "Sealed before the window" and download two files: Download as .txt (the line) and Download the timestamp proof (.ots).
  2. Go to opentimestamps.org. In "Stamp & Verify", drop the .ots file.
  3. When it asks for the stamped file, drop the .txt file. It is hashed in your browser, not uploaded.
  4. 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.