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

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.

Mon 26 Oct
EU session · v5
EUR/CHF
▼ Down 50% sure
✗ Miss
+9.8 pips
max up +18.0 · max down -2.6
Why this forecast
No news for the day was found and nothing pointed either way. A coin flip.
Model's technical note coin flip; no driver; no dated news: 6 searches returned only stale pages; snippets only - fetches blocked; L1 applies (no dated driver) - 50; Ifo 09:30 in window (no consensus); driver: none confirmed since 21:00; stats: pre-window +0.19 ATR; no statistical edge
Why it moved unclear
Euro jumped +12 pips in the first hour then faded after Ifo at 09:30 but held a net gain; no dated driver found
Fri 23 Oct
US session · v4
EUR/CHF
▼ Down 53% sure
✗ Miss
+10.3 pips
max up +19.3 · max down -11.7
Why this forecast
No clear news, but history showed a small rise before the session tends to reverse, so a small lean down.
Model's technical note no dated driver; L1 applies but EDGE says window reverses after pre-window up so tilted down 3 points; franc safe-haven bid on Hormuz risk unconfirmed today; driver: none confirmed since 21:00; stats: pre-window +0.21 ATR; EDGE reverse (LB 52.1 vs 49.1); no dated news: 8 searches returned only stale pages; snippets only - fetches blocked
Why it moved unclear
Dipped at 12:00 then rose from 14:00 and held the gain to the close; no dated driver found
Fri 23 Oct
EU session · v4
EUR/CHF
▼ Down 50% sure
✗ Miss
+10.9 pips
max up +15.6 · max down -12.8
Why this forecast
No clear driver for this pair: Middle East tension supported the franc while French worries hit the euro. A coin flip.
Model's technical note coin flip; no dated driver specific to EURCHF beyond Middle East safe-haven franc bid vs France worries; EZ flash PMI 08:00 cons 52.8 in window; driver: oil/risk sentiment mixed since 21:00; L1 applies (no driver; no EDGE) - 50; stats: pre-window +0.54 ATR; no statistical edge; snippets only - fetches blocked
Why it moved unclear
Dipped on the PMI hour then the cross rebounded from 10:00 as franc haven demand faded after a +14 pip pre-window gain; no dated driver found
Thu 22 Oct
US session · v4
EUR/CHF
▼ Down 52% sure
✓ Hit
-6.1 pips
max up +26.1 · max down -6.5
Why this forecast
Middle East tension sent money into the safe-haven franc, and the pair had already fallen in the morning. A small lean down.
Model's technical note Franc bid with Middle East safe-haven flow and EURCHF already -1.0 ATR pre-window; jobless claims 12:30 cons 200K in window; snippets only - fetches blocked; driver: risk/safe-haven bid persisting since 21:00 - 52; stats: prev day -0.18 ATR; EDGE continue (LB 53.1 vs 51.8) - tilted down
Why it moved plausible
Early rebound after the -50 pip pre-window drop faded from 17:00 as the Wall Street tech sell-off deepened and franc haven demand returned; closed slightly down
Thu 22 Oct
EU session · v4
EUR/CHF
▼ Down 51% sure
✓ Hit
-17.3 pips
max up +3.7 · max down -27.5
Why this forecast
French debt worries pushed investors toward the safe-haven franc, ahead of a credit-rating review of France. A weak lean down.
Model's technical note driver: French fiscal stress (OAT 5%; Euro Stoxx futures -0.6%) favours franc haven bid since 21:00 close; Moody's France review Oct 23; stats: pre-window -0.59 ATR; no statistical edge; snippets only; no lessons active
Why it moved plausible
Franc haven bid on French fiscal stress and weak European equities extended the Asia drop (-33 pips before 08:00)
Wed 21 Oct
US session · v4
EUR/CHF
▼ Down 52% sure
✓ Hit
-3.6 pips
max up +8.1 · max down -8.5
Why this forecast
No news for the day was found and no data was due. History pointed slightly lower after quiet days like this.
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; stats: pre-window -0.01 ATR and prev day -0.00 ATR EDGE continue (LB 50.6 and 53.0) - tilted down
Why it moved unclear
Drifted lower into the close after an early drop; very narrow range with no clear catalyst
Wed 21 Oct
EU session · v4
EUR/CHF
▼ Down 51% sure
✗ Miss
+1.7 pips
max up +9.1 · max down -10.7
Why this forecast
No news for the day was found and no data was due. Consistent with the calls on the other two pairs, a slight lean down.
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 - consistent with EURUSD down and USDCHF up; stats: pre-window -0.09 ATR; no edge
Why it moved unclear
Small two-way range; dip at 08:00 reversed up from 09:00 with no identifiable catalyst
Tue 20 Oct
US session · v4
EUR/CHF
▼ Down 52% sure
✗ Miss
+29.2 pips
max up +51.8 · max down -4.9
Why this forecast
French debt worries kept the euro soft, though there was little franc news. A small lean down.
Model's technical note No lesson active; no EU/CH/US release found (snippets only - fetches blocked; no Oct 20 news found); driver: euro soft on French debt stress since Monday (supports down) but franc news thin; stats: pre-window -0.27 ATR; EDGE continue (LB 49.3 vs 49.1) - tilted down
Why it moved clear
Euro rallied with risk as deal headlines pushed oil lower from 13:00-14:00 UTC; pair had already fallen 29 pips before the open
Tue 20 Oct
EU session · v4
EUR/CHF
▼ Down 51% sure
✓ Hit
-22.3 pips
max up +12.3 · max down -23.2
Why this forecast
French debt worries and the wide gap between US and euro interest rates kept the euro soft. Little franc news, so a weak lean down.
Model's technical note No lesson active; no EU/CH release found (snippets only - fetches blocked); driver: euro soft on French debt stress and wide US-EU yield gap since Monday (supports down) but franc news thin; stats: pre-window +0.10 ATR; no statistical edge
Why it moved plausible
Franc bid as rising oil hurt risk sentiment and the euro sagged all window
Mon 19 Oct
US session · v4
EUR/CHF
▼ Down 53% sure
✗ Miss
+1.0 pips
max up +7.6 · max down -10.8
Why this forecast
The franc gained on bets that the Fed would pause, and the pair was on a three-day slide at a 20-day low in a weak market mood. A modest lean down.
Model's technical note No lesson active; no in-window event found (snippets only - fetches blocked); driver: franc bid on Fed pause bets and EURCHF in a 3-day slide at the 20-day low with weak risk tone since Friday close - 53; stats: pre-window -0.20 ATR and prev day -0.23 ATR; EDGE continue (LB 50.6/53.0) - tilted down
Why it moved unclear
Cross traded flat in a narrow range after the strong morning rebound; no clear driver
Mon 19 Oct
EU session · v4
EUR/CHF
▼ Down 51% sure
✗ Miss
+34.3 pips
max up +35.1 · max down -3.0
Why this forecast
The franc gained as the dollar weakened, and riots in France added risk to the euro. The pair had dipped in the morning. A small lean down.
Model's technical note Snippets only - fetches blocked; no dated EURCHF-specific news; franc bid as USD weakens and French riots add euro risk premium; pre-window -12 pips; driver: franc safe-haven bid since Fri close (supports down); consistent with EURUSD up x USDCHF down; stats: pre-window -0.22 ATR; no edge
Why it moved plausible
Cross rebounded steadily after a 30 pip pre-open slide as the franc safe-haven bid and euro risk premium (French unrest) eased; no dated EURCHF news
Fri 16 Oct
US session · v4
EUR/CHF
▼ Down 51% sure
✓ Hit
-6.0 pips
max up +11.5 · max down -16.4
Why this forecast
No news for this pair was found, so the call relied on history, which pointed slightly lower. Only minor US data was due.
Model's technical note Snippets only - fetches blocked; no dated EURCHF news (ECB 29 Oct ~60% hike odds priced and SNB 0%) so the call leans on the stats; in window only minor US data (import prices 12:30; IP 13:15); no Active lessons; driver: ECB-vs-SNB spread unchanged since 21:00 - 51; stats: pre-window -0.05 ATR and prev day -0.68 ATR; EDGE continue (LB 50.6 and 52.6 vs 49.1 and 51.7) - tilted down
Why it moved plausible
Cross slipped on franc safe-haven demand in the risk-off afternoon after an early spike to +11 pips; no dated EURCHF news
Fri 16 Oct
EU session · v4
EUR/CHF
▲ Up 51% sure
✗ Miss
-3.4 pips
max up +4.8 · max down -9.4
Why this forecast
No news for this pair was found. It sat near 20-day lows with a small morning rise, so a mild bounce seemed slightly more likely.
Model's technical note No dated EURCHF-specific news (searches on ECB/SNB returned only stale items; ECB meets 29 Oct with ~60% hike odds priced and SNB at 0%); cross +0.17 ATR pre-window and near 20-day lows (10% of range) so mild mean-reversion up consistent with EURUSD up and USDCHF down; driver: ECB-hike vs SNB-hold spread unchanged since 21:00 - 51; stats: no edge
Why it moved unclear
Cross drifted lower on franc firmness after a 13 pip drop at 07:00 with no dated EURCHF news; range stayed under 15 pips
Thu 15 Oct
US session · v4
EUR/CHF
▼ Down 52% sure
✓ Hit
-32.7 pips
max up +2.3 · max down -35.3
Why this forecast
No news for this pair was found and it dipped slightly in the morning. US data in the afternoon was the main risk. History pointed slightly lower.
Model's technical note No dated EURCHF news (3 searches stale and forex.com/investinglive fetches failed); cross -8.6 pips (-0.15 ATR) pre-window with US PPI/retail 12:30 in window as the main risk; driver: none verified since 21:00 - 50 but EDGE continue tilts down; stats: pre-window -0.15 ATR; EDGE continue (LB 50.6 vs 49.1; prev day LB 53.0 vs 51.7) - tilted down
Why it moved plausible
Franc strength after the 12:30 data as Treasury yields fell amid geopolitical tension and risk-off; the cross dropped 24 pips in the first hour and kept sliding
Thu 15 Oct
EU session · v4
EUR/CHF
▼ Down 50% sure
✗ Miss
0.0 pips
max up +5.7 · max down -6.8
Why this forecast
No news specific to this pair was found, and it was flat in the morning. A coin flip.
Model's technical note No dated EURCHF-specific news; cross is flat pre-window (-0.5 pips) and EURUSD down plus USDCHF up nets roughly flat so a coin flip; searches for SNB/ECB 15 Oct returned only stale pages and fetches of FXStreet/investingLive/ActionForex failed - 50; stats: pre-window -0.01 ATR; no edge
Why it moved unclear
Flat cross range-bound around the open; no clear driver
Wed 14 Oct
US session · v3
EUR/CHF
▼ Down 51% sure
✓ Hit
-11.3 pips
max up +8.9 · max down -20.4
Why this forecast
No news was found. History suggested a small rise before the session tends to reverse, so a slight lean down.
Model's technical note No dated news found; EURUSD down and USDCHF up legs net flat; driver: none verified since 21:00 - 50 but EDGE reverse after small pre-window rise tilts down; stats: pre-window +0.13 ATR; EDGE reverse (LB 52.0 vs 49.1) - tilted down
Why it moved plausible
Little net effect of the CPI shock (euro and franc both fell vs the dollar); the franc strengthened late (17:00-18:00) as the USD rally unwound
Wed 14 Oct
EU session · v3
EUR/CHF
▼ Down 50% sure
✓ Hit
-3.7 pips
max up +6.4 · max down -5.1
Why this forecast
No news was found, and the euro and franc legs roughly cancelled out against the dollar. A coin flip.
Model's technical note No dated news found; EURCHF between EURUSD down and USDCHF up legs so net flat; driver: none verified since 21:00 - 50; stats: pre-window +0.10 ATR; no edge
Why it moved unclear
Small early pop then fade into the CPI release; no dated catalyst in the window
Tue 13 Oct
US session · v3
EUR/CHF
▼ Down 51% sure
✗ Miss
+9.1 pips
max up +15.4 · max down -3.8
Why this forecast
No news was found and the pair barely moved in the morning. History pointed slightly lower after an up day, so a small lean down.
Model's technical note No dated news found; small pre-window move (+0.05 ATR) and prior-day up; driver: none verified since 21:00 (no news edge) - 51; stats: EDGE reverse (LB 52.0 vs 49.1) - tilted down
Why it moved unclear
Euro rose steadily from 13:00 to 18:00 with no dated driver beyond the softer dollar tone; the franc strengthened vs the dollar but not vs the euro
Tue 13 Oct
EU session · v3
EUR/CHF
▼ Down 50% sure
✓ Hit
-7.8 pips
max up +0.9 · max down -10.2
Why this forecast
No fresh news was found and the dollar was moving in different directions against the euro and the franc. A coin flip.
Model's technical note No fresh news found; coin flip consistent with EURUSD down and USDCHF flat-to-up; driver: SNB/ECB policy unchanged and no new data found so none supports a call; stats: pre-window +0.05 ATR; no edge
Why it moved plausible
Franc strengthened as risk appetite improved and energy prices retreated; euro weighed down by French budget concerns
Mon 12 Oct
US session · v3
EUR/CHF
▼ Down 51% sure
✓ Hit
-0.7 pips
max up +15.3 · max down -1.7
Why this forecast
The pair had fallen three days running and the euro was soft against the dollar, so the morning bounce looked likely to fade. Only a slight lean.
Model's technical note Prev day down with 3-day streak and EURUSD soft; morning bounce of +0.29 ATR may fade; driver: no verified SNB/ECB change since 21:00 so no strong call; no lessons active; stats: prev day -0.35 ATR; EDGE continue (LB 52.9 vs 51.7) - tilted down
Why it moved unclear
Brief euro bounce into 14:00-15:00 then faded back to flat by the close; no dated driver found beyond broad dollar strength
Mon 12 Oct
EU session · v3
EUR/CHF
▼ Down 50% sure
✓ Hit
-8.0 pips
max up +1.5 · max down -9.5
Why this forecast
Zero Swiss interest rates kept the franc weak, but the pair had already fallen three days in a row and nothing new was due. A pure coin flip.
Model's technical note Franc kept weak by zero SNB rates but 3-day down streak and no catalyst; driver: SNB policy unchanged and no new data since 21:00 so no call; no lessons active; stats: pre-window +0.10 ATR; no edge
Why it moved plausible
Gradual drift lower after a strong pre-window bounce as the franc held up better than the euro while the euro was sold on French spread worries
Fri 9 Oct
US session · v2
EUR/CHF
▼ Down 51% sure
✓ Hit
-16.2 pips
max up +3.5 · max down -26.7
Why this forecast
The franc stayed in demand against a soft euro, with no European or Swiss news due. History pointed slightly lower after days like this.
Model'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 down
Why it moved unclear
Franc strength built from 15:00 to a low at 16:00 and held to the close; timing suggests a risk-off or safe-haven bid but no dated source found
Fri 9 Oct
EU session · v2
EUR/CHF
▼ Down 51% sure
✓ Hit
-5.5 pips
max up +8.3 · max down -8.6
Why this forecast
French budget worries and demand for the franc gave a slight lean down. No fresh news was found, so close to a coin flip.
Model's technical note French fiscal premium vs bid franc keeps slight downside lean; no fresh catalyst found; stats: pre-window +0.15 ATR; no edge
Why it moved unclear
Small drift lower after an early spike with the euro weak across the board; no clear driver found
Thu 8 Oct
Day session · v2
EUR/CHF
▼ Down 53% sure
✓ Hit
-7.6 pips
max up +15.7 · max down -14.0
Why this forecast
French political risk weighed on the euro while the franc stayed in demand. History also showed a slight tendency to fall in this situation.
Model'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 down
Why it moved plausible
French risk premium weighed on the euro in the morning (low -14 at 11:00) and the cross faded again from 16:00 after a brief US-session bounce; no single dated catalyst
Wed 7 Oct
Day session · v1
EUR/CHF
▼ Down 52% sure
✗ Miss
+7.2 pips
max up +16.9 · max down -24.8
Why this forecast
French political risk weighed on the euro while the franc stayed in demand. Only a slight lean, as the recent bounce could still continue.
Model's technical note French risk premium weighs on euro while franc safe-haven bid persists; slight lean as bounce could extend
Why it moved plausible
Most of the French-risk drop happened at 07:00 (0.9345 to 0.9320) before the window; EURCHF dipped to 0.9295 around 11:00 then rebounded with the euro and fading safe-haven bids
Tue 6 Oct
Day session · v1
EUR/CHF
▼ Down 54% sure
✗ Miss
+6.7 pips
max up +12.9 · max down -11.4
Why this forecast
French debt worries kept the euro weak, while the Swiss franc was in demand as a safe haven. Only a slight lean, as nothing new was expected during the day.
Model's technical note Euro weakness from French debt concerns plus safe-haven franc support with SNB floor at 0%; neutral intraday bias caps conviction
Why it moved plausible
French spread relief; most of the jump (0.9327 to 0.9353) came 07:00-08:00 before the window and the window only drifted a little higher
Mon 5 Oct
Day session · v1
EUR/CHF
▼ Down 53% sure
✗ Miss
+34.2 pips
max up +37.2 · max down -5.1
Why this forecast
Worries about French government debt had just caused a record one-day drop, and investors were buying the Swiss franc as a safe place. We expected that to continue.
Model'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 persist
Why it moved plausible
Same relief: the Asian plunge to 0.9277 on French debt fears unwound all day as the French spread narrowed and safe-haven franc demand faded
← NewerPage 2 of 2

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.