SShopOS /Halo lab
Runs in your browser
TIKTOK SHOP → AMAZON

Halo calculator

Bring your data. Explore the Amazon impact of your TikTok activity.

Your baseline, your scenario. Enter expected Amazon sales without TikTok. This mode calculates the difference; it doesn’t establish causality.

Your numbers

Period totals

Amounts: nonnegative numbers, up to 2 decimal places (e.g. 1250.55 or 1,250.55). No currency symbols. Maximum 1,000,000,000,000 per amount; blank optional amounts stay unknown.

a Amazon
Where to get actual Amazon sales
  1. In Amazon Seller Central, go to Reports → Business Reports.
  2. For the entire marketplace account, open Sales and Traffic by Date. For selected products, open Detail Page Sales and Traffic by Child Item.
  3. Set the exact start and end dates, include Ordered Product Sales, then choose Download (.csv).
  4. For selected products, filter to the approved child ASINs and sum Ordered Product Sales once. Do not add parent and child totals together.

The expected-sales baseline is not an Amazon export. It must come from a separately justified forecast or comparison using the same scope and sales definition.

Amazon’s Business Reports guide ↗
Add a baseline scenario range Optional

Enter both low and high plausible baseline totals, or leave both blank. The low value must be no greater than expected sales; the high value must be no less. This is a sensitivity range, not a calculated confidence interval.

♪ TikTok Shop Optional context
Where to get TikTok GMV and program costs
  1. For GMV, in TikTok Shop Seller Center go to Analytics → AI Report → Create New.
  2. Select GMV, use the same date range and program/product scope, then export the report and sum the applicable GMV.
  3. For platform-recorded fees and affiliate commissions, go to Finances → Statements or Payouts → Export and use the matching period.
  4. Add costs that are not in TikTok Shop separately, such as creator fees, samples, shipping, agency fees and other media.

Do not treat GMV as program cost or add it to the Amazon halo estimate.

TikTok Shop AI Report guide ↗
Costs may include media, creator fees, samples, shipping and commissions. TikTok GMV does not determine the Amazon estimate.

Nothing you enter is sent to a measurement server. Export before closing.

THE MEASUREMENT

What these numbers mean

Quick calculator

Scenario gap = actual Amazon ordered product sales − your supplied expected sales without TikTok. Lift = gap ÷ expected sales. The baseline drives this answer; the calculator cannot verify it from two sales totals.

If you enter a baseline range, the gap range is actual − high baseline through actual − low baseline. It is a user-defined scenario range, not an 80% or 95% confidence interval. Previous-period sales alone do not establish a counterfactual.

Daily data model

A signed linear model uses trend, weekday effects and one delayed TikTok view series. It evaluates 12 prespecified kernels with lags 0–28 days, decay 0.5/0.7/0.85 and peak 0/3/7/14. At 730 Amazon outcome days, annual Fourier terms are included. Optional control_ columns are standardized and held fixed under the comparison.

The point estimate uses the lowest-AIC candidate. The counterfactual removes all measured exposure, including warmup. It is a whole-program comparison, not a campaign effect. Fitted sales and actual sales differ by the model residual; the contribution is fitted actual-condition sales minus fitted zero-exposure sales.

Each of the 12 candidates receives 1,000 HC2-adjusted block-wild bootstrap replicates, with 14-day calendar blocks and seed 41017. Aggregate 80% and 95% ranges are the union of candidate percentile ranges. They describe uncertainty conditional on these modeling assumptions; they do not cover all omitted causes or establish real-shop causal validity.

Requirements and limits

At least 140 complete outcome days plus 28 exposure warmup days; continuous daily inputs; exposure CV ≥0.3; selected exposure VIF ≤5; at least five observations per parameter. This simple runner requires 100% complete outcomes and limits input to 1,096 outcome days. A block choice of 7 or 28 days can be run as sensitivity after the main result.

Predictive validation holds out three consecutive 14-day periods. Each fold chooses its lag from training outcomes only and compares against an otherwise identical no-TikTok model and a last-week seasonal baseline. Lower error does not prove causal attribution. Price, stock, other marketing and seasonal changes can explain the same sales movements. Causal support, placebo/negative-control tests, broader simulation validation and independent review are not completed by this tool. Daily model results are internal draft estimates, never automatically approved customer claims.

What to upload

Amazon: date and ordered product sales in one marketplace and currency. TikTok: date and verified daily total views, starting 28 days earlier. Use the same approved products and source-day boundaries. If data is missing, leave it blank; it won’t become zero.

The upload screen includes exact export paths for Amazon Seller Central and TikTok Shop Seller Center. Platform downloads must be reshaped into the ShopOS template; they are not accepted unchanged.

No customer names, order addresses, payment data or private creator contact information are needed. Every export retains inputs, scope, method and result status. Program-return scenarios require matched costs; they are not media iROAS or profit.