The client had issues with availability and profitability of food products in some of their stores.
The Forecast Inventory planners were not making data driven decisions but using expert judgment.
The client approached us to refine the forecast model so as to improve forecast accuracy.
A driver model was implemented to understand what factors drive forecast error in the system post which focused initiatives were planned and implemented across improving Seasonality patterns (Holt-Winters Model).
Improving Day of Week profiles (Modeled prior performance data)
Planning for Non-Seasonal Weather changes
Rule-Based Approach Planning for Promotions
Regression Modeling of Price Elasticity
A Spot fire Dashboard was designed and dedicated for reviewing the forecast
Accuracy for the past weeks which also highlights the defaulter in terms of worst forecast across Store Types and Products.
Better Understanding of Forecast Accuracy and its levers enabled the FIP's to make more informed decisions whenever necessary and reduced unnecessary interaction with the Forecasting and Ordering System.
Implementation of the above-mentioned initiatives led to a business benefit of ~£ 2.2 M profit and an improvement in availability from 92 % to 94% along with a reduction of 0.5% waste from 6.5% to 6% for the financial year.