Revenue ForecastingRevsure AIDec 2024 – PresentProduction

Time-Decay Forecast Adjustment

Dynamic adjustment layer that re-weights prior EOQ history by recency, capturing momentum and velocity signals closer to quarter end.

Production

Deployed

The Problem

Static average-based priors weighted all historical quarters equally, ignoring recent pipeline momentum or slowdown signals that are most predictive close to quarter end.

What Was Built

Built a time-decay adjustment layer that exponentially down-weights older EOQ observations, emphasizing recent quarters. Incorporates momentum, velocity, and capacity features. Deployed as a production adjustment layer on top of the base XGBoost forecast.

Business Impact

Improved late-quarter forecast accuracy by capturing recency signals, deployed to production as part of the Revenue Forecasting Platform.

Tech Stack

PythonXGBoostscikit-learnBigQuery

Domain Tags

Time-DecayBayesian UpdatingRevenue ForecastingMomentum Features

Details

Role
Primary Owner
Status
Production
Tier
Tier 1
Period
Dec 2024 – Present
Employment
Revsure AI