Inputs
Closed 5m bars and turnover of the instrument from ArcDelta.
TreVmS Labs · v1.0
Which hours of the day and days of the week are really different for this instrument?
Outputs
Return, volatility and turnover by UTC hour and weekday with 95% intervals, the share of up hours against the base rate, and which effects survive the multiple-testing correction.
Evidence
Over 20 days on 28 perpetuals, 376 of 3,276 tests passed the false-discovery control at q = 0.10: higher turnover and volatility at the US open (13:00–15:00 UTC) on 26 and 25 instruments, quieter weekends on about half. Return effects passed 6 times in total and the up-hour share never.
Limits
Describes the past, it is not a signal: return effects are rare and unstable. Each family of effects is corrected separately; those that fail are shown in grey. Spread is not covered yet: order-book history is too short.
API
GET /labs/seasonality?symbol=BTCUSDT
Minimum data: Five days of 5m bars.
Any account can run models within its plan quota; the standard liquidation map is free. Pricing →