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
USD/CHF
▼ Down 50% sure
✓ Hit
-1.0 pips
max up +1.3 · max down -30.8
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|USDCHF|down|50|0f1f014c81f32147046c11fec3fe7609
2. Its hash, published before the window
c379da4bda85a699cc8085f748d24ba6f3bb64e4d7317cd6d2ce14d38fda2c1e
sealed 11:17 UTC · OpenTimestamps: submitted 16 Nov 11:17 UTC
Download the timestamp proof (.ots)
Why this forecast
The dollar has been strong on rate-hike bets, but US yields eased since Friday and the Fed chair speaks late in the day. Neither side has a clear edge, so this is close to a coin flip.
Model's technical note Warsh speaks 17:00 in window (cap 55); driver: US 2y -1.8bp and 10y -1.1bp since 21:00 are against a dollar-up call and USDCHF follows yields r20 +0.37 - 50; coin: down; L1 applies (kept at 50); stats: pre-window +0.16 ATR; 7-day up streak; no edge
Why it moved plausible
Franc bid on risk-off (US-Iran headlines and a sinking Nasdaq) pushed it down to -31 by 15:00 then it recovered to flat as the dollar firmed; timing loose
Fri 13 Nov
US session · v6
USD/CHF
▲ Up 52% sure
✓ Hit
+14.7 pips
max up +17.9 · max down -18.8
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-13|us|USDCHF|up|52|793ebbea898fe03bfe5e462685f8142b
2. Its hash, published before the window
87170d542ea56fbee79680c66cc4052017c4ea7ffffa7f139413db714ee1de58
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
Higher US yields and Fed hike bets are lifting the dollar against the franc, and no Swiss news is due. Producer prices at 13:30 UTC could change that, so confidence is low.
Model's technical note US PPI 13:30 in window; yields and dollar firmed on Fed hike bets and Iran remarks; driver: US 10y +0.5bp since 21:00 (with up; small) while 2y -1.8bp mixed; r20 with 10y +0.32 - 52; stats: pre-window +0.25 ATR; no edge
Why it moved plausible
Dipped after the soft 13:30 PPI then recovered from 15:00 with the broad dollar bid on Fed hike bets; recovery has no dated trigger
Fri 13 Nov
EU session · v6
USD/CHF
▲ Up 50% sure
✓ Hit
+22.5 pips
max up +25.1 · max down -2.8
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-13|eu|USDCHF|up|50|4d9c5c288029da9ebf0aa275dc7f4fd4
2. Its hash, published before the window
c66fd744332af5b6eab27201877706ef0f1315ad2fbd47d9a8113b9df4d293a9
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 firm on expectations of a Fed rate hike but US bond yields have slipped overnight and nothing Swiss is due, so this is close to a coin flip.
Model's technical note Dollar strength on Fed hike bets but driver: US 2y -1.6bp and 10y -0.2bp since 21:00 are against up and no CHF driver dated; coin: up; L1 applies (kept 50); stats: pre-window +0.06 ATR; 98% of 20d range; EDGE continue - not used
Why it moved unclear
Steady CHF weakness through the window with no dated release; no clear driver
Thu 12 Nov
US session · v6
USD/CHF
▲ Up 50% sure
✓ Hit
+32.3 pips
max up +41.4 · max down -1.5
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|us|USDCHF|up|50|777e328dc131b068247c13da182702b1
2. Its hash, published before the window
d474c1880ecf1f0e2a55caf95751eeff194822432dbf137524e13fa4ad3ab773
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
Fed hike bets support the dollar but yields and stocks slipped overnight, so signals conflict and this is close to a coin flip.
Model's technical note No supporting driver: US yields -2.2bp since 21:00 and S&P futures -0.4% (r20 +0.33) both against up while Fed hike bets favour up; coin: up; claims 13:30 in window; L1 applies; stats: pre-window -0.22 ATR; no edge
Why it moved clear
Dollar rallied against the franc through the US afternoon in step with the surge in Treasury yields and Fed hike bets; main leg 14:00-17:00 UTC
Wed 11 Nov
US session · v6
USD/CHF
▲ Up 53% sure
✓ Hit
+37.2 pips
max up +43.3 · max down -2.2
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-11|us|USDCHF|up|53|9ede54840e9de3afdeb13e28c96320dc
2. Its hash, published before the window
a10ce5e11945bbea74b046f2e99fa1166502207b8ece80e41f8d3db1b3360289
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
Firmer US interest rates after yesterday's hot inflation data should lift the dollar against the Swiss franc. No major data is due and holiday trading is thin, so this is only a slight lean.
Model's technical note Same dollar-supportive story after hot CPI and hawkish Waller; no scheduled US data in window; driver: US 2y +2.2bp since 21:00 (with up; r20 +0.26); US holiday x0.85 range; snippets only; stats: pre-window +0.47 ATR; no edge
Why it moved plausible
Dollar rose against the franc in the same 13:00-14:00 UTC burst (about 30 pips) and held; US Treasury market closed for Veterans Day and no scheduled data so the dollar bid had no single dated trigger
Wed 11 Nov
EU session · v6
USD/CHF
▲ Up 51% sure
✓ Hit
+20.0 pips
max up +22.0 · max down -2.5
Sealed late
1. The forecast, written as one line
date | session | pair | direction | confidence | secret. This exact line was hashed.
fx2owl-fx-v1|2026-11-11|eu|USDCHF|up|51|923215950b1e662aebb090e109ca1d77
2. Its hash, published before the window
d9043f8b8e3d8ea45a79fd6698eb0453f11c249f8e361f05fe27f01dbff89b42
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
Higher US yields after hot inflation data slightly favour the dollar against the franc. No Swiss news is due, so this is only a small lean.
Model's technical note Same US yield story; driver: US 10y +2bp since 21:00 (with up) but r20 only +0.22 and no Swiss data; L1 n/a; stats: pre-window +0.24 ATR; EDGE continue - not used
Why it moved plausible
Steady dollar-franc climb through the window as the dollar stayed bid after hot US CPI and hawkish Fed repricing; no Swiss or EU data
Tue 10 Nov
US session · v6
USD/CHF
▲ Up 52% sure
✓ Hit
+43.5 pips
max up +58.4 · max down -13.0
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|us|USDCHF|up|52|e6a49c15960245ae620be433f700e366
2. Its hash, published before the window
3333ee331a7e70d72ad5413dabad5f96618bd2f62bdb80c2de545b3e4692d137
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
US inflation data is due at 13:30 UTC and rising US yields slightly favour the dollar, so USD/CHF leans higher. A soft number would reverse this.
Model's technical note US CPI Oct 13:30 cons 0.2% core m/m in window; Waller hawkish; driver: US 2y +5bp since 21:00 (with up) - 52; snippets only; stats: pre-window +0.26 ATR; no edge
Why it moved clear
Hot US CPI at 13:30 UTC lifted US yields and the dollar; USDCHF rose about 50 pips by 15:00-16:00 UTC and held most of it
Tue 10 Nov
EU session · v6
USD/CHF
▲ Up 50% sure
✓ Hit
+26.5 pips
max up +27.8 · max down -5.4
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|USDCHF|up|50|37d776a6a9c848f14a4190a43dc38c7b
2. Its hash, published before the window
58f1a3aad464d8496e16215a0f79939a94dc3fb750d7d3ca23360292e8a3e3fa
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 Swiss or euro-area news is due this morning and US yields are flat ahead of the afternoon US inflation report, 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 10y -0.2bp since 21:00 flat; S&P +0.21% r20 +0.27 weak (not against); coin: up; stats: pre-window -0.16 ATR; EDGE reverse - not used
Why it moved plausible
Dollar jumped about 25 pips at 09:00 UTC and held while traders positioned for hot US CPI after Waller's hawkish 50bp remarks; no dated release at 09:00
Thu 5 Nov
US session · v6
USD/CHF
▼ Down 52% sure
✓ Hit
-8.1 pips
max up +5.7 · max down -46.9
Why this forecast
A slightly softer dollar should nudge the dollar against the Swiss franc a bit lower. US jobless claims later could change that, so confidence is low.
Model's technical note Mirrors EURUSD dollar-softness view from lower yields and Congress fiscal outlook (snippets only); claims 13:30 cons 196K in window; driver: US 10y -0.7bp since 21:00 (with down; tiny) - 52; stats: pre-window +0.09 ATR; no edge
Why it moved unclear
Dollar-franc dropped sharply from 14:00 and recovered late; franc strength with no dated catalyst found
Mon 2 Nov
US session · v6
USD/CHF
▼ Down 50% sure
✓ Hit
-22.9 pips
max up +0.5 · max down -27.8
Why this forecast
The signals conflicted and the pair had already fallen sharply that day. A coin flip.
Model's technical note coin flip; drivers conflict: USDCHF already -0.6% on the day with yields flat and S&P +0.5% (r20 +0.40) pointing up while Brent -4.5% (don't trust) points down; ISM 15:00 cons 54.7 in window; L1 applies and coin: down; stats: pre-window -0.76 ATR; no edge
Why it moved plausible
Dollar-franc fell on franc strength; the ISM beat only gave a brief bounce at 15:00 before the slide resumed
Fri 30 Oct
EU session · v5
USD/CHF
▼ Down 53% sure
✓ Hit
-14.7 pips
max up +4.0 · max down -16.9
Why this forecast
US interest rates fell to one-month lows overnight and nervous markets favoured the safe-haven franc. A modest lean down.
Model's technical note driver: US 10Y -1bp since 21:00 after one-month-low yields overnight (with down; r20 +0.55); risk-off bid for CHF; L1 n/a (dated news); stats: pre-window -0.13 ATR; EDGE reverse - not used
Why it moved plausible
Franc strength continued with lower US yields and risk-off; the dollar kept sliding toward the US open
Tue 27 Oct
US session · v5
USD/CHF
▲ Up 50% sure
✓ Hit
+1.8 pips
max up +7.2 · max down -7.5
Why this forecast
US interest rates eased overnight, which works against a dollar rise, and traders were cautious ahead of the Fed meeting. A coin flip.
Model's technical note Coin flip no driver: US 10y -1.8bp since 21:00 moved against up (r20 +0.59 with 10y); L1 applies; durable goods 12:30 and CB confidence 14:00 in window; pre-FOMC caution; stats: prev day +0.77 ATR; EDGE reverse - not used
Why it moved unclear
Choppy range with no direction until a late 20:00 bid; pre-FOMC positioning and no confirmed driver
Tue 27 Oct
EU session · v5
USD/CHF
▲ Up 50% sure
✓ Hit
+9.3 pips
max up +13.6 · max down -0.6
Why this forecast
US interest rates edged down overnight, which works against a dollar rise, and the calendar was quiet. A coin flip.
Model's technical note Coin flip no driver: US 10y -0.9bp since 21:00 moved against up (r20 +0.59 with 10y) so no support; quiet EU calendar; L1 applies; set 50; stats: pre-window +0.16 ATR; EDGE continue - not used
Why it moved plausible
Dollar bid versus the franc through the session on the same firm-yield USD tone; no dated release in window
Mon 26 Oct
US session · v5
USD/CHF
▲ Up 50% sure
✓ Hit
+7.7 pips
max up +12.2 · max down -14.4
Why this forecast
No news for the pair was found and the small move in US interest rates was too small to matter. A coin flip.
Model's technical note coin flip; no driver; no dated pair news: 5 searches + investinglive fetch; tradingeconomics blocked; snippets only; L1 applies (no dated driver) - 50; FOMC Oct 28 and PCE/GDP Oct 29 outside window; no major US release in window; driver: US 10y +0.9bp since 21:00 (with up; r20 +0.6) too small - 50; stats: prev day +0.89 ATR; EDGE reverse - not used
Why it moved plausible
Dipped at 12:00 then dollar strength from 14:00 held a gain to the close; no dated release in window
Mon 26 Oct
EU session · v5
USD/CHF
▲ Up 50% sure
✓ Hit
+17.0 pips
max up +17.1 · max down -3.3
Why this forecast
No news for the day was found and US interest rates dipped slightly overnight. 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; driver: US 10y -1.1bp since 21:00 (against up) - 50; stats: pre-window -0.12 ATR; EDGE reverse - not used
Why it moved unclear
Franc weakened at the open and again into 11:00 with a dip around the Ifo release; no dated driver found
Fri 23 Oct
US session · v4
USD/CHF
▲ Up 50% sure
✓ Hit
+3.6 pips
max up +12.8 · max down -23.8
Why this forecast
No news drove the pair and only a US business survey was due. A coin flip.
Model's technical note coin flip; no dated driver; US flash PMI 13:45 in window; driver: none confirmed since 21:00; L1 applies (no driver; no EDGE) - 50; stats: pre-window +0.40 ATR; no statistical edge; no dated news: 8 searches returned only stale pages; snippets only - fetches blocked
Why it moved unclear
Sharp dollar drop at 12:00-13:00 reversed from 14:00 to a small gain at the close; no dated driver found
Fri 23 Oct
EU session · v4
USD/CHF
▲ Up 50% sure
✓ Hit
+15.8 pips
max up +16.6 · max down -11.5
Why this forecast
US interest rates had fallen sharply, which works against the dollar, while the franc was in demand. Nothing clearly supported a rise. A coin flip.
Model's technical note coin flip; yields fell sharply since Oct 22 (against up) while franc bid on Middle East tension so no supporting driver; pre-window rebound +25 pips; L1 applies (no driver; no EDGE) - 50; stats: pre-window +0.53 ATR; no statistical edge; snippets only - fetches blocked
Why it moved unclear
Dollar rebound against the franc continued after the +24 pip pre-window gain with a dip at 09:00 and a rise from 10:00; no dated driver found
Thu 22 Oct
US session · v4
USD/CHF
▼ Down 52% sure
✓ Hit
-17.2 pips
max up +22.8 · max down -17.7
Why this forecast
US interest rates were falling from multi-year highs as bets on a US rate rise faded, and the franc was in demand as a safe haven. A small lean down.
Model's technical note US 10Y falling from multi-year high 5.14% as Fed hike bets fade (DXY -0.5 since 21:00) plus safe-haven franc bid; jobless claims 12:30 cons 200K in window; snippets only - fetches blocked; driver: yields down since 21:00 (supports down) - 52; stats: pre-window -0.76 ATR; no edge
Why it moved clear
Early dollar bounce after the claims beat reversed from 15:00 as Treasury yields tumbled and the Nasdaq sank
Fri 16 Oct
EU session · v4
USD/CHF
▼ Down 51% sure
✓ Hit
-16.5 pips
max up +3.3 · max down -23.7
Why this forecast
US interest rates fell as the odds of a US rate rise dropped, and the dollar eased overnight. That favoured the franc. A small lean down.
Model's technical note US yields fell ~9bp after hot PPI 1.3% and retail sales 0.8% as Oct Fed hike odds dropped to ~30% and the dollar eased in Asia so the rate-spread driver favours down; no CH or EZ release found in window; driver: US 10Y -9bp since 21:00 supports down; stats: pre-window -0.08 ATR; EDGE reverse (LB 52.3 vs 50.0) opposes - kept down at 51
Why it moved plausible
Dollar weakness on faded Fed hike bets and lower US yields pushed USDCHF down 18 pips by 10:00 extending the overnight slide
Thu 15 Oct
EU session · v4
USD/CHF
▲ Up 52% sure
✓ Hit
+2.3 pips
max up +5.6 · max down -19.3
Why this forecast
Hot US inflation kept bets on a US rate rise high and the pair near multi-month highs, but the dollar had faded in the morning. A small lean up.
Model's technical note Hot US CPI kept Fed-hike pricing elevated and USDCHF sits near highs since May 2025 but is -39 pips (-0.76 ATR) pre-window as the dollar faded so the yield driver is mixed since 21:00 - 52; no EU-window release found; stats: prev day +0.48 ATR; EDGE continue (LB 52.2 vs 50.8) - tilted up
Why it moved plausible
Dip in the first hours as the dollar kept fading from its 18-month high then stabilised before US PPI; no dated catalyst in the window
Wed 14 Oct
US session · v3
USD/CHF
▲ Up 50% sure
✓ Hit
+17.1 pips
max up +63.6 · max down -1.3
Why this forecast
No news was found and the pair had risen slightly in the morning near the top of its recent range. A coin flip.
Model's technical note No dated news found; small +0.17 ATR pre-window rise at 77% of 20-day range; driver: none verified since 21:00 - 50; stats: pre-window +0.17 ATR; prev day -0.35 ATR; no edge
Why it moved clear
Hot US CPI at 12:30 (core +0.3% vs 0.2% expected) revived Fed-hike bets and the dollar jumped vs the franc; about two thirds retraced by the close
Wed 14 Oct
EU session · v3
USD/CHF
▲ Up 51% sure
✓ Hit
+2.1 pips
max up +8.8 · max down -1.6
Why this forecast
No news was found. The pair sat in the upper part of its recent range after a small dip, and history pointed slightly higher. A weak lean up.
Model's technical note No dated news found; small -0.07 ATR pre-window dip at 71% of 20-day range; driver: none verified since 21:00 (no news edge) - 51; stats: pre-window -0.07 ATR; prev day -0.35 ATR; EDGE reverse (LB 52.3 vs 50.0) - tilted up
Why it moved unclear
Small dollar bid carried over from the 07:00 bar ahead of US CPI; no dated catalyst in the window
Mon 12 Oct
US session · v3
USD/CHF
▲ Up 51% sure
✓ Hit
+16.1 pips
max up +18.4 · max down -3.7
Why this forecast
The dollar was firm and the franc weak, but the pair had already risen strongly in the morning. A low-confidence lean that the move holds.
Model's technical note Dollar firm and franc pressured by zero SNB rates but +0.62 ATR already priced this morning; driver: rate spread unverified since 21:00 (not against up) - low confidence; no lessons active; stats: pre-window +0.62 ATR; no edge
Why it moved plausible
Dollar gained from 14:00 to 15:00 on the oil and safe-haven dollar bid and held it to the close with the franc the weakest major
Mon 12 Oct
EU session · v3
USD/CHF
▲ Up 51% sure
✓ Hit
+13.0 pips
max up +16.8 · max down -1.4
Why this forecast
The dollar held up and zero Swiss rates kept the franc soft. No fresh news was found, so confidence was low.
Model's technical note Dollar resilient and franc pressured by zero SNB rates; no fresh news found; driver: rate spread unchanged since 21:00 (supports up) - low confidence; no lessons active; stats: pre-window +0.13 ATR EDGE continue (LB 51.4 vs 50.4) and prev day -0.30 ATR EDGE reverse (LB 51.9 vs 50.9) both point up - tilted up
Why it moved plausible
Franc was the weakest major vs the dollar on the day; the dollar bid on oil and geopolitical demand lifted the pair in the first hours of the window
Fri 9 Oct
EU session · v2
USD/CHF
▲ Up 53% sure
✓ Hit
+11.6 pips
max up +15.7 · max down -1.2
Why this forecast
Expectations of tighter US policy and firm US interest rates supported the dollar. News was thin, so only a modest lean up.
Model's technical note Hawkish Fed repricing and firm yields support dollar; thin news; stats: pre-window -0.12 ATR and prev day -0.27 ATR; EDGE reverse (LB 52.2 vs 50.0) - tilted up
Why it moved unclear
Dollar rebounded in the first hour after a -17 pip pre-window drop and held the gain; no dated catalyst found
Wed 7 Oct
Day session · v1
USD/CHF
▲ Up 51% sure
✓ Hit
+3.9 pips
max up +13.1 · max down -12.0
Why this forecast
The Fed's meeting notes and speeches could lift the dollar after a dip, but demand for the safe-haven franc limited the upside. Close to a coin flip.
Model's technical note Hawkish FOMC minutes and Fed speakers could lift the dollar after a dip but franc safe-haven demand caps gains; near coin flip
Why it moved unclear
Choppy range 0.8317-0.8342 with a mild dollar bid into the Fed minutes; no decisive catalyst so the gain was small

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.