Optimizer
Get Optimizer Settings
Returns the bid optimizer's mode, whether auto mode is unlocked, and the latest bid-model backtest.
Update Optimizer Settings
Sets the bid optimizer mode and returns the full optimizer settings (same shape as Get Optimizer Settings). The change is recorded in the activity log.
Preview Bid Optimizer
Runs the bid optimizer as a dry run: it computes bid-model estimates and builds a simulated change set, with the explanation on every line, but nothing is applied to the ad platforms. Runs asynchronously as a tracked background job; poll the returned `tracked_job_log_id` for progress and the per-account results. The preview runs even when the optimizer mode is `off`; accounts whose data is stale are skipped.
Run Bid Optimizer
Runs the bid optimizer now for the given ad accounts, outside the nightly schedule. Runs asynchronously as a tracked background job; poll the returned `tracked_job_log_id`. Per account, the optimizer refreshes the bid-model estimates and proposes goal-based bid changes (plus ad-rate changes on eBay and target changes on TikTok and Google). What happens next depends on the effective optimizer mode: `off` skips the run, `monitor` stores the estimates only, `suggest` creates a pending change set that must be approved, and `auto` submits the change set for automatic application. Products in the control arm of a holdout experiment keep their bids. Accounts whose data is stale are skipped.
Backtest Bid Model
Starts an offline backtest of the bid model over the given ad accounts: the model is trained on the first half of the history and scored on the second, comparing its calibration and contribution against the bid-to-target-POAS rule. Runs asynchronously as a tracked background job; poll the returned `tracked_job_log_id`. The result is stored and shown as `backtest` in Get Optimizer Settings; a passing result unlocks the optimizer's `auto` mode for the validity window (30 days by default).
List Bid Estimates
Lists the latest bid-model estimate for each target (keyword or product target) in one ad account: own clicks, the posterior conversion-rate mean and credible interval, average order value, the value of a click and the recommended bid, plus the target's current expression, match type, bid, state and campaign. Sorted by `value_per_click`, highest first. Paginated, 10 per page by default (max 200).