The recent news that Tesco is to sell green satsumas, after hotter than average temperatures in Spain prevented the fruit from turning its usual orange colour, reflects growing consumer acceptance of grocery products that do not necessarily conform to conventional standards, as well as recognition by the retail industry that they must do more to reduce food waste.
Bridging the gap between farm and fork
Reducing food waste is becoming an increasingly important issue, with celebrities championing the cause and statistics on the quantity of produce wasted by supermarkets appearing in the national media. With retailers bridging the gap between farm and fork and responsible for contributing approximately one third of the 18 million tonnes of food that ends up in landfill, they must to ensure that they are using all the tools available to them to reduce the amount of food that they waste and optimizing their stock levels.
We are seeing rapidly growing awareness among customers of the issue of food waste. Any retailer that wants to be perceived as a socially responsible, ethical business, must demonstrate that they are making real efforts to reduce the amount of food that either isn’t sold due to cosmetic reasons, or is thrown away having spoiled before it is purchased. It is very encouraging to see that Tesco has taken the decision to ignore its own quality specifications and sell fruit that may look unusual but is perfectly good to eat.
Implementing artificial intelligence as a tool for change
Reducing food waste is not just good practice from a social responsibility perspective, it also makes very good economic sense. Every piece of food that is sold rather than wasted is profit generated for the retailer’s bottom line. Machine learning is the key to this as retail is a data-rich business, with vast reams of information available on past sales patterns, customer footfall, product prices and external data such as public holidays, even the weather, and the impact these factors have on customer demand. When combined with advanced machine learning technology, stock replenishment optimization solutions can then make accurate predictions of customer demand and help retailers to carry the appropriate levels of stock, across thousands of product categories and hundreds of stores. Using the data at their disposal, retailers can react more quickly and with more agility to rapidly changing market conditions and customer demands.
How can replenishment optimization reduce waste?
Blue Yonder Replenishment Optimization is a machine learning solution that allows automated store replenishment to efficiently reduce waste. The solution utilises a wide variety of data points to create accurate and granular forecasts of customer demand, with a weighted optimization of waste levels and product availability, its automated decisions reducing the burden of making manual interventions on retailers.
Find out more about Blue Yonder Replenishment Optimization and what it could do for your retail organisation, here.