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

31 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.

Thu 12 Nov
EU session · v6
USD/CHF
▲ Up 51% sure
✗ Miss
-0.8 pips
max up +2.3 · max down -9.6
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-12|eu|USDCHF|up|51|b308b0c1df55ac13e560d96a8ab68f16
2. Its hash, published before the window
c61f0f9a7a8433aace2b7ba788f9a2df7cb02febef9c64032d95f580b8b6a617
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
Expectations of more Fed rate hikes support the dollar against the franc, but yields have not moved much overnight and risk sentiment is soft, so this is only a slight lean up.
Model's technical note Fed hike bets lift the dollar (index highest since Apr 2025) but driver US yields flat since 21:00 (2y 0.0bp; 10y +0.7bp) and S&P futures -0.5% (r20 +0.33 against up) so little support - 51; pair at 91% of 20d range; stats: pre-window 0.0 ATR; EDGE reverse - not used
Why it moved unclear
Dollar slipped slightly against the franc in a flat range ahead of US claims; no EZ or CH news in the window
Mon 9 Nov
US session · v6
USD/CHF
▼ Down 50% sure
✗ Miss
+8.4 pips
max up +41.8 · max down -0.8
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|USDCHF|down|50|634f886e3b30ce8ed5074929c6950e42
2. Its hash, published before the window
debcbb8a088673d5b29dc82a465045667cd38e4c75af181f08192a009fbd0cbe
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
Only a few Fed speeches are scheduled and the key US inflation data comes tomorrow, so nothing clearly favours the dollar or the franc. This is close to a coin flip.
Model's technical note L1 applies (no clear dated driver; US yields flat since 21:00 and S&P +0.55% r20 +0.36 mildly with up but small); coin: down; Fed speakers only in window; stats: pre-window -0.43 ATR; EDGE continue - not used
Why it moved unclear
Dollar-franc jumped about 30 pips at 14:00 UTC then faded most of it by close; no dated catalyst found for the 14:00 move
Mon 9 Nov
EU session · v6
USD/CHF
▼ Down 52% sure
✗ Miss
+5.4 pips
max up +7.8 · max down -5.3
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|eu|USDCHF|down|52|aa24df255420f8bd3998e5a9381a8c39
2. Its hash, published before the window
60820ea3bed5185710c8f78f43f2507296dc191c6fe1cb430a2c11f2c0af2313
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
The dollar is broadly softer and US yields have eased a little, so the dollar should slip against the Swiss franc. Nothing important is due to change that this morning.
Model's technical note L1 does not apply (dated driver: broad dollar softness; US 10y -1.35bp since 21:00 (with down)); no Swiss data in window; stats: pre-window -0.21 ATR; EDGE reverse - not used
Why it moved unclear
Dollar-franc ranged within about 13 pips after a 24 pip pre-window slide; no clear driver
Fri 6 Nov
US session · v6
USD/CHF
▼ Down 50% sure
✗ Miss
+21.9 pips
max up +39.0 · max down -2.4
Why this forecast
No clear Swiss news is due; the US jobs report at 13:30 UTC could move the dollar either way. This is close to a coin flip.
Model's technical note L1 applies (no dated Swiss driver; snippets and two fetches only) so coin flip; coin: down; US NFP 13:30 cons 65K in window; driver: none reliable (S&P fut +0.23% r20 +0.27 weak); stats: pre-window +0.25 ATR; no edge
Why it moved clear
US payrolls 165K vs 65K expected with unemployment 4.1% lifted the dollar and yields at 13:30 and dollar-franc rose about 25 pips
Fri 6 Nov
EU session · v6
USD/CHF
▼ Down 51% sure
✗ Miss
+3.7 pips
max up +11.5 · max down -11.9
Why this forecast
No important Swiss or European news is due. Slightly weaker stocks and flat US yields give a very small lean toward a softer dollar against the franc; this is close to a coin flip.
Model's technical note US NFP 13:30 is after the window; L1 applies (no dated Swiss news; snippets only) so near coin flip; driver: S&P fut -0.29% since 21:00 (with down; r20 +0.27 weak) and US 10y -1bp - 51; stats: pre-window -0.14 ATR; EDGE reverse - not used
Why it moved unclear
Dollar-franc chopped in a narrow range with a slight upward bias into payrolls; no dated Swiss catalyst
Thu 5 Nov
EU session · v6
USD/CHF
▼ Down 50% sure
✗ Miss
+25.5 pips
max up +31.3 · max down -1.2
Why this forecast
No important Swiss or US news falls in this morning window and the franc already moved overnight, so this is close to a coin flip with a slight lean to a lower dollar.
Model's technical note L1 applies (no dated driver; snippets only - fetches blocked); coin: down; driver: US 10y -2.9bp since 21:00 (r20 -0.08 no link) - 50; stats: pre-window -0.56 ATR at 4% of 20d range; no edge
Why it moved unclear
Dollar-franc rebounded steadily after an Asia-session drop; no dated catalyst found
Wed 4 Nov
US session · v6
USD/CHF
▲ Up 51% sure
✗ Miss
-3.0 pips
max up +14.7 · max down -25.7
Why this forecast
Rising stocks tend to weaken the franc, and the pair had fallen a lot in the morning, leaving room for a bounce. Dollar weakness after the midterms was the risk. A weak lean up.
Model's technical note driver: S&P fut +1.05% since 21:00 (r20 +0.45 supports up); US 10y -0.45bp not a link (r20 -0.14); pre-window -0.8 ATR at 6% of range leaves room for a bounce but midterm dollar weakness is the counter story; ADP 13:15 and ISM Services 15:00 in window; stats: no edge
Why it moved plausible
Dollar-franc fell after the 13:15 ADP then recovered to flat by 14:00 and went sideways; the risk-on bounce did not extend
Wed 4 Nov
EU session · v6
USD/CHF
▼ Down 53% sure
✗ Miss
+9.1 pips
max up +18.4 · max down -11.0
Why this forecast
The dollar was sold after the midterm results and stock futures were lower, which favours the franc. Much of the move was already done. A modest lean down.
Model's technical note driver: S&P fut -0.19% since 21:00 (r20 +0.45 supports down) and USD sell-off after midterm results; US 10y -2bp (r20 -0.14) not against; EZ CPI 10:00 in window; pre-window -0.72 ATR already priced; L1 does not apply; stats: pre-window -0.72 ATR; no edge
Why it moved plausible
Dollar-franc bounced from the overnight midterm low (-47 pips before 08:00) with a step up at 10:00; the sell-off was already priced
Tue 3 Nov
US session · v6
USD/CHF
▼ Down 52% sure
✗ Miss
+15.5 pips
max up +23.2 · max down -13.2
Why this forecast
Higher-than-expected Swiss inflation and slightly lower stock futures supported the franc. US job-openings data and the midterms were risks. A small lean down.
Model's technical note driver: S&P fut -0.12% since 21:00 (r20 +0.42 supports down) and hot Swiss CPI +1.5% vs +1.3% exp lifts CHF; US 10y +1.8bp (r20 -0.18) not against; JOLTS 15:00 cons 7.06M and midterms in window; L1 does not apply; stats: pre-window -0.03 ATR; no edge
Why it moved plausible
Dollar-franc firmed with a step up around the 15:00 JOLTS and held; the franc did not extend its strength
Tue 3 Nov
EU session · v6
USD/CHF
▼ Down 53% sure
✗ Miss
+31.1 pips
max up +35.0 · max down -11.0
Why this forecast
Swiss inflation came in higher than expected, which supports the franc, and stock futures were lower. A modest lean down.
Model's technical note driver: Swiss Oct CPI 07:30 +1.5% vs +1.3% exp lifts CHF and S&P fut -0.34% since 21:00 (r20 +0.42 with down) while US 10y +0.9bp flat; L1 does not apply; stats: pre-window -0.08 ATR; EDGE reverse not used
Why it moved plausible
Dollar-franc rebounded all morning after a -18 pip drop before the open (Swiss CPI 07:30 hot print); the franc strength was priced before 08:00 and then faded
Mon 2 Nov
EU session · v6
USD/CHF
▲ Up 50% sure
✗ Miss
-21.4 pips
max up 0.0 · max down -36.2
Why this forecast
The signals conflicted: lower US interest rates pointed down, rising stocks pointed up. A coin flip.
Model's technical note coin flip; no driver: yields -1.8bp favour down but S&P +0.5% (r20 +0.40) favours up so the drivers conflict; L1 applies and coin: up; stats: pre-window -0.32 ATR; no edge; EDGE continue not used
Why it moved unclear
Franc strength extended the pre-window slide (-23 pips) with no dated catalyst so the dollar-franc up call missed
Fri 30 Oct
US session · v5
USD/CHF
▼ Down 52% sure
✗ Miss
+43.7 pips
max up +50.5 · max down 0.0
Why this forecast
Falling US interest rates and nervous stock markets favoured the franc, though the pair had already fallen in the morning. A small lean down.
Model's technical note driver: US 10Y -2.9bp since 21:00 (with down; r20 +0.55) and risk-off (S&P -0.5%; VIX +1.2) favours CHF; ECI 12:30 in window; already -0.56 ATR pre-window; L1 n/a; stats: no edge
Why it moved plausible
Dollar jumped on opening of US session (ECI in line at 0.8%) and extended after soft German CPI weakened EUR; US 10Y yield rebounded and risk-off unwound
Thu 29 Oct
US session · v5
USD/CHF
▲ Up 50% sure
✗ Miss
-42.1 pips
max up +13.1 · max down -44.5
Why this forecast
US growth and jobless data were due, and US interest rates had eased overnight, which works against a dollar rise. A coin flip.
Model's technical note US GDP/claims 12:30 in window; L1 applies (no dated pair driver; snippets only - fetches blocked); coin flip; driver: US 10y -1.4bp since 21:00 (against up so 50); stats: pre-window +0.18 ATR; no edge
Why it moved plausible
Dollar slid against the franc after the 13:15 ECB hold with December hike talk lifted the euro and hit USD; extra drop from 20:00 as USDCHF broke below its 100-hour average; no news found for that last leg
Thu 29 Oct
EU session · v5
USD/CHF
▼ Down 51% sure
✗ Miss
+1.7 pips
max up +8.1 · max down -6.0
Why this forecast
The Fed held and the dollar barely moved. US interest rates and gold edged lower overnight. A weak lean down.
Model's technical note Fed hold left USD little changed (snippets only); no in-window release; L1 applies (no pair-specific driver); driver: US 10y -1.1bp since 21:00 (with down; r20 +0.56 beta 3.3 pips/bp) and gold -1% - 51; stats: pre-window +0.15 ATR; EDGE not used
Why it moved unclear
Small two-way range before the 12:30 US data and ECB; no clear driver
Wed 28 Oct
US session · v5
USD/CHF
▲ Up 53% sure
✗ Miss
-17.3 pips
max up +13.1 · max down -20.9
Why this forecast
The Fed was expected to hold rates with a tough tone while the Swiss central bank stayed at zero, so the dollar looked firm. Capped confidence because of the Fed press conference.
Model's technical note FOMC 18:00 UTC hawkish hold priced (Warsh press conf in window so cap 55) with SNB on hold at 0% and USD firm; driver: US 10y +0.9bp since 21:00 (with up; r20 +0.59); investinglive says initial USD rise may fade - kept modest; stats: pre-window +0.27 ATR; no edge
Why it moved plausible
Dollar slid against the franc from 16:00 and fell hard after the 18:00 FOMC decision as the initial USD rise faded; exact message not confirmed in sources
Wed 28 Oct
EU session · v5
USD/CHF
▲ Up 52% sure
✗ Miss
-3.2 pips
max up +6.9 · max down -3.4
Why this forecast
The dollar was in demand ahead of the Fed decision, with US interest rates and oil rising. A small lean up.
Model's technical note snippets only - tradingeconomics blocked; pre-FOMC dollar bid with oil rally; driver: US 10y +2.3bp since 21:00 (with up; r20 +0.59); stats: pre-window +0.39 ATR; no edge
Why it moved unclear
Dollar bid faded after the 07:00 reversal and the pair slipped below the open by 11:00 in thin pre-FOMC trade; no dated release
Thu 22 Oct
EU session · v4
USD/CHF
▼ Down 51% sure
✗ Miss
+11.2 pips
max up +17.6 · max down -17.3
Why this forecast
The dollar weakened on expectations of a Fed pause, but much of that had already happened in the morning. A weak lean down.
Model's technical note driver: USD weaker on Fed-pause expectations since 21:00 (supports down) but pre-window -0.71 ATR already prices much; prev-day EDGE reverse (LB 52.0) offsets; stats: pre-window no edge; snippets only; no lessons active
Why it moved plausible
Dollar bounced from a one-month low after a -33 pip Asia slide on Fed-pause bets; the decline was already priced before 08:00 and the window was a partial reversal
Wed 21 Oct
US session · v4
USD/CHF
▲ Up 51% sure
✗ Miss
-2.9 pips
max up +13.4 · max down -9.8
Why this forecast
No news for the day was found and no data was due. Consistent with the euro call, a weak lean up.
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 - consistent with EURUSD down; stats: pre-window +0.22 ATR; no edge
Why it moved unclear
Early dip then a 14:00-15:00 rally of about 15 pips that faded by the close; no dated catalyst found
Wed 21 Oct
EU session · v4
USD/CHF
▲ Up 52% sure
✗ Miss
-1.2 pips
max up +11.6 · max down -6.3
Why this forecast
No news for the day was found and no data was due. History pointed slightly higher, so a small lean up.
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 +0.12 ATR EDGE continue (LB 50.7) and prev day -0.37 ATR EDGE reverse (LB 52.1) - tilted up
Why it moved unclear
Rose about 10 pips in the 09:00 hour then gave it all back by 12:00; no dated catalyst found
Tue 20 Oct
US session · v4
USD/CHF
▼ Down 52% sure
✗ Miss
+7.5 pips
max up +25.4 · max down -15.2
Why this forecast
US interest rates eased in the morning and markets expected the Fed to hold, which limits the dollar's upside. History also pointed lower. A small lean down.
Model's technical note No lesson active; no US release found (snippets only - fetches blocked; no Oct 20 news found); driver: US yields eased in the morning (USDCHF -19 pips pre-window) and Fed Oct 28 hold odds ~84% cap upside - 52; stats: pre-window -0.35 ATR; EDGE continue (LB 52.5 vs 49.7) and prev day +0.62 ATR EDGE reverse (LB 50.7 vs 49.7) - both point down
Why it moved plausible
Pair dipped early then rose as deal headlines lifted risk and weakened the franc; fully fading after oil swung back
Tue 20 Oct
EU session · v4
USD/CHF
▲ Up 52% sure
✗ Miss
-7.0 pips
max up +8.9 · max down -7.1
Why this forecast
US interest rates rose with oil, which supports the dollar, but markets expected the Fed to hold, which limits conviction. A small lean up.
Model's technical note No lesson active; no release found (snippets only - fetches blocked); driver: US yields up since Monday on oil rebound (supports up); Fed Oct 28 hold odds ~84% limit conviction; stats: pre-window -0.18 ATR; EDGE reverse (LB 52.3 vs 50.0) - tilted up
Why it moved unclear
Dollar gains faded as oil-driven risk-off lifted the franc late in the window; no dated trigger
Mon 19 Oct
US session · v4
USD/CHF
▼ Down 51% sure
✗ Miss
+16.3 pips
max up +20.3 · max down -8.0
Why this forecast
Lower US interest rates and fading bets on a US rate rise favoured the franc, though the pair bounced a little in the morning. A weak lean down.
Model's technical note No lesson active; no in-window event found (snippets only - fetches blocked); driver: US yields and hike bets lower since Friday (supports down) though USDCHF bounced +14 pips this morning - 51; stats: pre-window +0.24 ATR; reverse LB 50.1 but no edge
Why it moved unclear
Dollar bounce from 14:00 UTC (+17 pips by 15:00) as the morning euro rally unwound; no dated trigger identified
Mon 19 Oct
EU session · v4
USD/CHF
▼ Down 51% sure
✗ Miss
+1.2 pips
max up +6.2 · max down -11.3
Why this forecast
The franc was supported as US interest rates fell and bets on a US rate rise faded. A small lean down.
Model's technical note Snippets only - fetches blocked; USDCHF ~0.8240 with franc supported as US yields fell and Fed hike bets faded (hold odds ~84%); driver: US yields down since Fri 21:00 (supports down); stats: pre-window -0.05 ATR and prev day -0.46 ATR; EDGE reverse (LB 52.3) opposes so kept confidence at 51
Why it moved unclear
Choppy range around the open with no net move as dollar and franc moves offset; no clear driver
Fri 16 Oct
US session · v4
USD/CHF
▼ Down 51% sure
✗ Miss
+8.4 pips
max up +29.2 · max down -12.7
Why this forecast
Falling US interest rates after strong data cut the odds of a US rate rise, which favoured the franc over the dollar. Only minor US data was due. A weak lean down.
Model's technical note Snippets only - fetches blocked; US 10Y -9bp since 21:00 after hot PPI and retail sales cut Fed hike odds so the rate-spread driver favours down; in window US import prices 12:30 and IP 13:15 with no consensus found; no Active lessons; driver: US 10Y -9bp since 21:00 supports down - 51; stats: pre-window -0.54 ATR and prev day -1.44 ATR; no edge
Why it moved plausible
Dollar bounce on risk-off (AI-stock selloff and credit stress) lifted USDCHF 23 pips by 16:00 UTC after a 36 pip fall before the window; partial give-back into the close
Thu 15 Oct
US session · v4
USD/CHF
▲ Up 51% sure
✗ Miss
-35.9 pips
max up +14.1 · max down -38.4
Why this forecast
The pair had fallen sharply in the morning as the dollar faded after hot inflation data. US producer prices and retail sales in the afternoon could revive the dollar. A weak lean up.
Model's technical note USDCHF fell -53 pips (-1.02 ATR) pre-window as the dollar faded after hot CPI so the Fed-hike driver moved against the call since 21:00; US PPI 12:30 cons 0.5% and retail sales in window could restore the bid; kept up for consistency with EURUSD down and cross flat - 51; no dated 15 Oct news found (3 searches stale and fetches failed); stats: pre-window -1.02 ATR; no edge
Why it moved clear
Hot PPI failed to lift the dollar; falling Treasury yields and franc safe-haven demand drove USDCHF down 30 pips after 12:30 and it kept falling into the close
Tue 13 Oct
US session · v3
USD/CHF
▼ Down 50% sure
✗ Miss
+1.2 pips
max up +9.3 · max down -11.0
Why this forecast
No news was found. After a big rally the franc had recovered a little in the morning, and the pair sat near the top of its recent range. A coin flip with a slight lean down.
Model's technical note No dated news found; franc rebounded -0.33 ATR in the morning after +1.0 ATR rally and pair sits at 75% of 20-day range; driver: US yield direction unverified since 21:00 - 50; stats: EDGE continue (LB 52.6 vs 49.7) vs no edge after big prior day - slight down tilt
Why it moved unclear
Choppy range with no direction: dipped 11 pips at 13:00 then recovered to flat while dovish Fed talk and a softer dollar index offset each other ahead of CPI
Tue 13 Oct
EU session · v3
USD/CHF
▲ Up 50% sure
✗ Miss
-6.6 pips
max up +3.2 · max down -9.8
Why this forecast
No fresh news was found. The pair jumped the day before and slipped a little in the morning, with nothing to support a call either way. A coin flip.
Model's technical note No fresh news found; pair rose +1.0 ATR yesterday but slipped -0.31 ATR pre-window; driver: rate spread unverified since 21:00 so none supports a call; stats: prev day +1.01 ATR; no edge
Why it moved plausible
Dollar demand weakened as the index pulled back from its 18-month high and the franc firmed; drift lower through the window
Fri 9 Oct
US session · v2
USD/CHF
▲ Up 52% sure
✗ Miss
-10.9 pips
max up +8.1 · max down -14.9
Why this forecast
Swiss interest rates at zero kept the franc under pressure while US rates stayed firm. Little news was due, so a small lean up.
Model'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 edge
Why it moved unclear
Early dollar gain faded after 15:00 as the franc bid built into the close (same move as EURCHF); no dated catalyst found
Thu 8 Oct
Day session · v2
USD/CHF
▲ Up 52% sure
✗ Miss
-15.3 pips
max up +15.0 · max down -25.1
Why this forecast
The dollar was supported by expectations of tighter US policy and high US interest rates. The pair was already near a 20-day high, so only a small lean up.
Model'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 edge
Why it moved plausible
Dollar held a bid through the European session but sold off hard from 17:00 as US yields pulled back and the franc firmed; the hawkish-Fed support did not carry into the evening
Tue 6 Oct
Day session · v1
USD/CHF
▲ Up 51% sure
✗ Miss
-5.4 pips
max up +5.0 · max down -22.8
Why this forecast
Higher US interest rates supported the dollar, but demand for the safe-haven franc kept capping its gains. Close to a coin flip with a small lean up.
Model'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 lean
Why it moved unclear
Small range day; franc slightly firmer against a dollar easing alongside the euro rebound; no clear driver
Page 1 of 2Older →

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.