Inaccurate demand plans result in poor service levels, which was at a low 45%.
The Before State
Rudimentary forecasting process with each function operating with a different view of overall demand resulted in inefficient service delivery process.
Combined forecasts from different algorithms (ARIMA, ETS, TBATS or Holt-Winters) to boost accuracy. Forecasts were evaluated monthly and recalibrated as appropriate.
The After State
Demand forecasting accuracy went up to 92% from 65% reducing lead time by 20%. 4% increase in First Time Completes resulting in an incremental revenue of $5 million per annum due to reduced cancellations.