Creative factor backtester

Backtest the creative,
not the spend.

A quant factor backtester, pointed at ad creative. Run a thumbstop model over past posts and grade how well it ranks them by attention before you spend. Same toolkit equity quants use: information coefficient, decile spread, walk-forward. Data is synthetic, wired to the real schema.

Run a backtest
30%
Opt-in partner data
Information coeff (IC)
forecast vs realized · rank IC
ICIR · info ratio
signal Sharpe · mean IC / IC vol
Top-decile lift
long leg vs niche average
Hit rate
directional accuracy, top decile

Finance terms: IC is the forecast-to-outcome rank correlation, the standard factor-signal metric (0 is noise, 0.1+ is real edge). ICIR is the information ratio of that IC, the signal's Sharpe. Lift is the long leg vs average. Breadth is sample size, and IR is roughly IC times the square root of breadth.

Gains curve · cumulative capture
keep top X% ranked, capture Y% of views
ModelHuman pickRandomOracle
Decile spread · long-short
mean views by predicted decile (D1 low → D10 high)
Walk-forward IC
information coefficient per time period · stability is the point
How to run it
  1. Universe pick the niche, that is the factor's domain
  2. Features tag each creative point-in-time, no lookahead
  3. Split train on the past, test out-of-sample on the future
  4. Grade IC, ICIR, decile spread, gains vs baselines
  5. Walk forward roll the window, confirm the signal holds
  6. Deploy only if it clears the bar, else kill it cheap
The data structure · click a column to sort

Every post is a row.

The table the model trains and tests on: creative and context as point-in-time features, views and clicks as the forward label. Synthetic rows, exact columns. pred is the model's rank score.

assetcreative_idplatform formataestheticangle hook / copypersonadayhr viewsclickspred
What's working now · the signal feed

The live read per niche.

This is what a contributor sees: the formats, hooks, and post windows pulling above average right now, scoped to their niche. Follows the niche selected in the backtest above.

Top formats
    Best post windows (mean views)
    The money pitch

    Cut the weak before you pay for it.

    The model kills the bottom 30% before spend. Enter your numbers, see the wasted test budget you stop burning. Reallocation upside sits on top of this.

    Wasted test budget saved
    Annualized
    Spend reallocated off weak creative
    Give to get · the data flywheel

    Free audits in. Sharper model out.

    Agencies harvest your data quietly. We make it a fair trade. We run a free audit, you opt in to share de-identified outcomes, the niche pool grows, every contributor's predictions get sharper. The audit is the front door, the pool is the moat.

    Free audit
    score their creative
    Opt-in share
    de-identified rows
    Niche pool grows
    more labeled data
    Model sharpens
    better-fit weights
    Better audits
    flywheel turns
    Watch it compound
    Audits collected120
    — rowsIC —
    The deal

    Contribute rows, get the model

    You give de-identified outcomes. You get predictions trained on the full pool, not your thin slice. The contributor advantage compounds as the pool grows.

    The guardrail

    Pool reads, raw stays private

    Per-brand rows never leave your tenant. Only aggregate, thresholded, stripped signal feeds the shared model. No creative, caption, or brand identity is exposed.

    Run a free audit →