POST/forecastsadmin
Register a forecast BEFORE the moment it is for (409 once target_at has passed): value and 10–90% band, how it was made, an inputs hash (or inputs to hash), and the naive baselines' values for skill.
Body
subject | what is forecast |
target_at | ISO date/time it is for |
value | number |
low | 10% quantile |
high | 90% quantile |
method | name (e.g. swarm+release) |
design | design key |
run | run id |
inputs | anything; hashed (sha256, canonical JSON) when inputs_hash is absent |
inputs_hash | |
baselines | {name: value}, e.g. {last: 120, no_change: 0} |
GET/forecastsmember
Registered forecasts, by target date, each with its outcome once scored.
Query
subject | |
method | |
scored | true | false |
limit | 1..500 (50) |
DELETE/forecasts/:idadmin
Remove a registered forecast and its outcome.
POST/forecasts/actualsadmin
Post actuals; every open forecast for that subject and day, made before it, is scored at once (absolute and percentage error, sMAPE, pinball, within band, error of each baseline).
Body
actuals | [{subject, at, value}] (or one at the top level) |
source | where they came from |
POST/forecasts/actuals/pulladmin
Pull actuals from one of the tenant's read-only tools (called with {subject, ...args}, answering {actuals: [{at, value}]}) and score them.
Body
tool | tool name |
subject | |
args | {} |
GET/forecasts/ledgermember
The accuracy ledger: per method, design or the whole tenant: scored count, MAE, MAPE, sMAPE, pinball, band coverage, skill against each baseline (1 - MAE/MAE baseline), month by month; per design also its backtests' skill.
Query
by | method | design | tenant |
subject | |