Can an AI Trading Track Record Be Verified?
Median quoted spread and the cost of a $25,000 round trip: midday hour, July 15, 2026ranking ·
2026-08-03 · 6×3
SPY holding-period outcomes since 2015: 5th percentile, median, 95th percentiletable ·
2026-08-03 · 4×7
How far SPY travels from its opening print, by ET half hour, first half of 2026series ·
2026-08-03 · 13×3
Six US index funds, identical window: price return, January 2 to June 30, 2026ranking ·
2026-08-03 · 6×3
AI Daily Market Research Reports: What Breaks
SPY: average overnight repricing vs average regular-session move, monthlyseries ·
2026-08-01 · 24×3
What the next session did: 36 large caps bucketed by the prior day's move, Aug 2024 to Jul 2026table ·
2026-08-01 · 5×5
When headlines actually land: article counts by ET clock hour, July 2026ranking ·
2026-08-01 · 24×4
Headline coverage by size of daily move: 36 large caps, May to July 2026ranking ·
2026-08-01 · 5×4
Daily turnover in the top ten movers: fixed 36 name large-cap list, July 2026series ·
2026-08-01 · 21×3
Multi-Agent AI Trading Systems: What Is Real
The window decides the answer: SPY calendar-year price return and intra-year high-to-low range, 2016-2025ranking ·
2026-07-31 · 10×4
Where the money trades: US dollar volume by liquidity rank tier, regular hours, June 30 2026ranking ·
2026-07-31 · 5×4
How big a typical session is: SPY close-to-close moves by size band, calendar 2025ranking ·
2026-07-31 · 5×3
The cost floor: median quoted spread in basis points of the midpoint, regular hours, June 22-26 2026ranking ·
2026-07-31 · 6×4
Median quoted spread and the cost of a $25,000 round trip: midday hour, July 15, 2026
Median quoted spread and the cost of a $25,000 round trip: midday hour, July 15, 2026
| ticker | median_spread_bps | round_trip_cost_per_25k_usd |
|---|---|---|
| MSTR | 10.08 | 25.2 |
| MSFT | 2.01 | 5.03 |
| NVDA | 1.43 | 3.59 |
| AAPL | 1.24 | 3.09 |
| KO | 1.21 | 3.01 |
| SPY | 0.27 | 0.66 |
the exact SQL behind every number
SELECT ticker,
round(quantileDeterministic(0.5)(20000 * (toFloat64(ask_price) - toFloat64(bid_price))
/ (toFloat64(ask_price) + toFloat64(bid_price)),
cityHash64(sip_timestamp)), 2) AS median_spread_bps,
round(25000 * quantileDeterministic(0.5)(2 * (toFloat64(ask_price) - toFloat64(bid_price))
/ (toFloat64(ask_price) + toFloat64(bid_price)),
cityHash64(sip_timestamp)), 2) AS round_trip_cost_per_25k_usd
FROM global_markets.cache_stocks_quotes
WHERE ticker IN ('SPY', 'AAPL', 'MSFT', 'NVDA', 'KO', 'MSTR')
AND sip_timestamp >= toDateTime('2026-07-15 15:00:00')
AND sip_timestamp < toDateTime('2026-07-15 16:00:00')
AND bid_price > 1
AND ask_price > bid_price
GROUP BY ticker
ORDER BY median_spread_bps DESC
More from this analysisCan an AI Trading Track Record Be Verified?
Six US index funds, identical window: price return, January 2 to June 30, 2026
ranking 6×3
→
How far SPY travels from its opening print, by ET half hour, first half of 2026
series 13×3
→
SPY holding-period outcomes since 2015: 5th percentile, median, 95th percentile
table 4×7
→
When market headlines publish, by New York clock hour
ranking 24×2
→
See all 2,170 queries →