Insights/Measurement

Predictive demand forecasting from marketing signals.

Ad spend, clicks and search interest move before sales do. Used together with sell-through data, they forecast demand early enough to avoid stock-outs and overstock.

Bespoke ResearchMeasurement4 min read

The context

Capsule drops create demand peaks that last two to three weeks. Peaks that short are hard for a traditional supply chain to follow. Marketing data is the earliest signal a brand has.

A hybrid model

  • ARIMAX, a time-series model, with ad spend lagged by seven days as an external input.
  • LightGBM, a gradient-boosting model, using spend from seven days earlier, clicks from three days earlier, Google Trends interest in the brand and a weather index.

Five steps to production

  1. Collect ad spend and event data every day.
  2. Engineer features such as lags and rolling averages.
  3. Split data into training and test sets with rolling-origin validation.
  4. Back-test forecast error (MAPE) against sell-through.
  5. Deploy on Vertex AI and trigger purchase-order suggestions automatically.

How to report it

  • Actual against forecast demand.
  • Feature importance with SHAP values.
  • A heatmap of forecast error by product class.

Notes

First published on bespokemarketing.asia and updated for this site. Figures are as cited in the original article; tool defaults are examples unless stated.