Skip to main content

Weighting curve for product recommendations

Product recommendations use a weighting curve to prevent old data from skewing results and surfacing less relevant products.

Written by Gareth Burroughes
Updated yesterday

By default, product recommendations consider all historical data. The weighting curve adjusts this by prioritising recent activity, so the products recommended to your contacts are based on what's most relevant now.

The weighting curve calculates scores based on event recency, from the first event, an order or page view for example, to the most recent.

curve.png

The weighting curve strongly favours more recent events. Only items placed in the last 20% of the timeline receive a weighted score above 0.5. From there, the weighting rises rapidly to 1.


Custom weighting curves

The weighting curve calculates scores based on event recency, from the first event, an order or page view for example, to the most recent.

To try a custom weighting curve, contact your Customer Success representative.

Did this answer your question?