OSD / Studio / Params

Params — live config diff vs studio winner

How Params works

The Studio Agent runs grid sweeps over your settled-position history and produces a "winner" config — the parameter set that maximized realized ROI on historical data. This page diffs the winner against your currently-deployed live config, so you can see what the data is suggesting that you haven't applied yet.

What it shows

Side-by-side: live value vs. studio-recommended value for every config key the agent touched.
The delta direction (looser / tighter) and magnitude.
Optional gate: only show changes that the agent flagged as "high confidence" (n large enough, ROI delta meaningful, not borderline).

When NOT to apply a recommendation

Negative scoped values that violate runtime invariants. The Studio's combined patch has historically produced invalid negative scopedMinQk entries that the agent rejects on apply. Flagged in daily packets.
Out-of-sample regimes. If the sweep ran on data that includes a sport season that's now ended (e.g. NFL), don't promote settings for sports not currently in scope.
Small-n cells. Per-(book, league, market, mode, flow) cells with fewer than ~10 settled bets are noise — the agent may flag this with a "thin sample" warning.
Gates with known bugs (e.g. pre-fix alignMaxOddsDiff). If the agent's recommended threshold is calibrated against a broken gate, applying it doesn't fix anything.

Workflow

Studio Agent runs (manually or via daily-packet automation).
This page surfaces the diff.
You review change-by-change, decide which to apply.
Apply by writing to user config (the Studio Agent page can do this directly).
Watch for a few days; if a change misbehaves, roll back.

Workflow tool. Not a runtime gate. Daily packets that produce these recommendations are tracked in the tmp/run_daily_osd_config_analyst.js automation.

Data

Remote API Base URL

Remote User ID

Remote API Key

Load remote positions to begin.

Controls

Run Settings

Run Mode

Objective Metric This is the score the optimizer maximizes when ranking candidates.

Minimum Bets for Recommendation Requires at least this many bets for a recommendation to be eligible.

Sweep Setup

Single sweep tests one knob across a range.

Parameter

Explicit Values (comma list, optional)

From

Step

Minimum Sharps Required 0 disables sharp-count gating.

Max Combo Evaluations Run-engine safety cap for Grid and Sharp sweeps (not a segment filter).

Guardrails

Min Distinct Days Requires recommendations to span at least this many settled days. Set 0 to disable.

Max Worst-Day Degradation ($) Rejects recommendations when worst-day profit drops by more than this amount. Set 0 to disable.

Min Green Day Rate (0-1) Requires this minimum share of profitable days for recommendations. Set 0 to disable.

Segment Filters

Sub-selection filters below are applied after Run Mode + Objective Metric.

Flow

Mode

League

Book

Market Family

Data Quality & Output

Optional Config Overrides JSON (applied last)

Missing Data Policy

Rows to Show

Load remote positions to start.

Summary

Rows Loaded

Settled Matched

Baseline (ROI)

Best Delta

Baseline snapshot: ROI -, Profit -, Win Rate -, Bets -

This is historical replay on bets you already took. It cannot estimate bets that were never placed.

Parameter results are ranked here first. In Auto mode, charts below use the top-ranked parameter row.

Param	Baseline	Best	Bets	Baseline Score	Best Score	Delta

Run a single-parameter sweep or Auto mode to populate these charts.

Shaded band = top-performing value zone (top 20% by selected objective metric).

Gold dot = best score in this sweep.

Line + dots = metric result for each tested value.

X-axis = tested parameter value.

ROI Curve

Run a single-parameter sweep (or Auto mode) to render ROI curve.

Profit Curve

Run a single-parameter sweep (or Auto mode) to render profit curve.

Win Rate Curve

Run a single-parameter sweep (or Auto mode) to render win-rate curve.

Bet Count Curve

Run a single-parameter sweep (or Auto mode) to render bet-count curve.

Distribution

Rows are tested parameter values. Each row shows aggregate results for that value.

Parameter Value	Bets	Pass Rate	Distinct Days	Green Day %	Worst Day	Win Rate	ROI	Profit	Stake	Avg EV