Project Description

WEATHER RESPONSE MODEL

Is there a practical way to optimise stock levels in response to changes in the weather?”

We developed a reliable weather response model for Waitrose, a major UK supermarket chain with 290 branches stocking 20,000+ different product lines. Lost sales for stocks affected by weather, could be reduced by 6% and wastage by 1%, leading to a reduction in costs of around 2%.

Bays Consulting worked with logistics expert Dr Andrew Eaves of Andalus Solutions, to develop a  weather response model for Waitrose, a major UK supermarket chain. Waitrose has 290 branches stocking 20,000+ different product lines.

Their existing automated demand forecasting system accounted for the day of the week, time of year, bank holidays and circumstances such as promotions. Waitrose wanted to improve on this by incorporating data from weather forecasts.

Historical data on demand and weather patterns obtained from the nearest weather station to each branch was analysed and significant relationships uncovered. As a result, demand forecasts were updated using multipliers when specific weather patterns were predicted. The impact of the new estimates on ordering dates and quantities was determined, and the costs of lost sales and wastage were assessed using simulation. Clustering techniques were then developed for combining branches and lines which shared similar demand responses to weather.

Our analysis demonstrated, for those commodities where sales were affected by weather, that lost sales could be reduced by 6%. We also showed that wastage could be reduced by 1%, leading to a reduction in costs of around 2%. The supermarket business is a low-margin industry, with the average profit margin typically ranging from 1 to 2 per cent, so this result was considered significant.