There’s a lot of talk about artificial intelligence (AI) as the next best thing since sliced bread. But what does AI really mean for the food industry and what are the implications, asks Stephanie Duvault-Alexandre?
According to a report by Accenture, 85 per cent of organisations have planned to adopt digital or AI technologies in their supply chains during the last year. It’s clearly becoming big business across industries. The value of AI is estimated to be worth $36.8bn globally by 2025 predicts US market intelligence firm Tractica.
AI is not necessarily a concept that’s all that new. Various names refer to more or less the same thing. For example, machine learning is used to steer self-driving cars. AI is proving instrumental in healthcare for identifying and diagnosing complicated ailments. In Fintech, all stock markets are now dominated by computer decision-making systems. And even everyday search engines like Google use AI to refine and improve their results the moment you tap in a few keywords.
Despite a lot of talk about artificial intelligence at the moment, there aren’t that many vendors with machine learning already imbedded in their software. The early adopters of AI include mainly pharmaceutical, healthcare, cosmetics and retail industries. So far, we’ve found the food and beverage industries to be not quite so advanced in terms of AI adoption in their supply chain planning processes; but nonetheless, they’re starting to foresee the value that machine learning can bring.
The obvious benefits of machines over humans are efficiency and speed. But the majority of companies we’re speaking to about AI are more driven by the promise of additional revenues, better margins and lower costs. Increased efficiencies in the food supply chain are getting harder to achieve. Many companies think they’ve already done most of what can be expected using yesterday’s technology solutions and supply chain optimisation processes.
And that’s where artificial intelligence comes in. AI relies on a continual process of technological learning from experience and getting better and better at answering complex questions. Algorithms powered by AI can rapidly come up with alternative options which are otherwise much more time-consuming and laborious using conventional computer-powered A/B testing. Like the human brain, AI adapts to the environment and gets better the more you use it. But unlike humans, the capacity for improvement is unlimited. What’s more, boring, repetitive tasks are never a problem.
With most food manufacturers and retailers having thousands of customers and products to deal with on a daily basis, machine learning is proving much more efficient at unravelling complex data quickly and meaningfully. For instance, retailers want to be able to cluster and identify who are their main customers – who are repeat purchasers, browsers, or so-called aliens. Or they might need to know which products are better to deliver last-minute; or which core lines should regularly be in stock.
And with many retailers dependent on promotions for contributing between 20 and 30 per cent of sales – particularly in grocery – machines can tell us which promotions are better. Machine learning is more effective at clustering promotions based on looking at similarities and many more variables than is otherwise possible using traditional, linear-based forecasting techniques. For instance, a leading health food company used machine learning to analyse demand variations and shopping trends during promotions, resulting in a 30 per cent reduction in lost sales.
Software starts with creating baseline forecasts for what particular products should ideally be stocked, where and when. AI-powered algorithms learn from a multitude of factors that are likely to influence buyer behaviour – including promotions, social media, or the weather – which then are used to more accurately manage inventory levels and replenishment. Not only will such advanced technology know when shelves are empty, but more importantly, it will predict what will happen next. This means that shelves remain fully stocked and waste (or discounting) is minimised.
Waste not, want not
In food industries in particular, many are looking at new ways of reducing waste, which remains a problem today: current estimates put UK households and food industries wasting around ten million tonnes of food a year, valued at over £17bn, according to figures from WRAP, the UK waste advisory body. A few food processing companies have already turned to artificial intelligence as a means to better calibrate their machines in order to manage several products sizes and reduce waste and costs. Others have been able to identify the optimal use of raw materials – like vegetables or fruit – dependent on size and varieties. For example, one potato processing company has turned to AI to define which potatoes will produce the least waste when cut into French fries and which ones would work best for potato crisps. Some beverage companies have even used AI to rank flavour preferences among consumers – armed with an app on their phone in front of a self-service machine, customers could opt to change the flavour of their chosen drink – as part of developing new product ranges.
One of the biggest growth areas where AI can make a significant difference is in intelligent forecasting systems. Previously, retailers and manufacturers were only able to predict roughly the quantities of products to order to keep shelves fully stocked using (often out-of-date) inventory levels and historical sales data (usually going back a few years, at best). These days, AI can develop a much more accurate picture of exactly what types of products are likely to sell, by looking at multiple scenarios in real time (suppliers’ data, consumer behaviour, the weather etc.) and drawing on data from the internet. This means forecasting is no longer so much ‘stab in the dark’ guess work.
So, next time you marvel about the wonders of Amazon’s Alexa when ordering some food, think about its canny ability to second guess your next move. Artificial intelligence might just be the order of the day.
The UK’s leading supplier of continental snacks to retailers, Winterbotham Darby, has been able to stay on top of food shopping trends – such as increased sales of olives during warm weather, or rising demand for low-salt ranges and discounted lines – after implementing sophisticated forecasting technology that uses algorithms to pinpoint seasonal fluctuations in demand. The Futurmaster software helps plan promotions and manage the ordering of raw materials and packaging across a wide range of cold meats and fresh ingredients from multiple suppliers and manufacturers across Europe. Improved planning has led to reductions in stock holdings and more streamlined deliveries to supermarkets.
Simon Dancy, group planning manager at Winterbotham Darby, said he hopes to be able to use new developments in machine-learning from Futurmaster to predict promotion performance with greater accuracy and speed, taking into account many more outside factors to determine the forecasted sales uplift.
Stephanie Duvault-Alexandre is a business consultant at FuturMaster, which supports more than 500 customers across 90 countries, including Heineken, L’Oréal, Danone Waters, Lactalis, Pepsico and LVMH, with advanced supply chain solutions and industry expertise. FuturMaster solutions enable companies to achieve higher customer service levels and effective cost management by optimising sales and operations planning and end-to-end demand and supply planning processes.