With few brick-and-mortar shopping experiences on offer during lockdown, there’s been little option but to shop online. We’ve already seen online sales increase 27% from the same time year-on-year, and by 23% in just one week in April.

And while consumer buying habits have been shifting towards ecommerce for a few years now, the pandemic has accelerated this. The chances are that the more accustomed consumers become to online shopping with the various fulfilment options, and convenience this offers, the more likely they are to stick with it, even when social distancing measures are removed.

That leaves a huge question mark for retailers as to how to reengineer their supply chains to fulfil the demands of the ‘omnichannel imperative’.

 

Artificial Intelligence (AI) to the rescue

That’s where AI comes in. It offers one of the most significant ways for retailers to respond to this step change in ecommerce as it encompasses a whole range of algorithms supporting business processes like optimising web search, targeting advertisements, approving consumer loans, routing delivery trucks, forecasting consumer demand and allocating inventory.

Let’s look at which use cases are most relevant to addressing the omnichannel imperative, and how retail supply chains need to adapt.

 

Supply chain design

A first stage in addressing the step change in omnichannel business is the design of the supply chain network. The network of distribution centres, dark stores and traditional stores needs to be able to fulfil orders through methods like ship from distribution centre, ship from store or pickup from store. Traditional AI techniques can be used to design the fulfilment network to meet these demands by helping retailers to:

•  Determine the optimal number and location of warehouses and e-fulfilment nodes or start a greenfield evaluation
•  Plan for warehouse and transportation capacity through optimal SKU-location mapping with network product flows and stocking levels
• Determine the required capacity and product flows to handle returns
• Plan optimal labour requirements at fulfilment centres

 

Demand sensing

To succeed and thrive in this retail shift, organisations will also benefit from being more demand driven. They must be able to predict where demand will occur across brick-and-mortar and online channels, and efficiently fulfil the right quantity of products to thousands and even millions of locations.

Demand sensing makes use of Machine Learning (ML) techniques to enable pattern recognition and eliminate supply chain lags, by continuously learning and reducing the time between demand signals such as order frequency, order size, distribution centre/store inventory, POS and the response to those signals.

Forecasting with demand sensing techniques typically uses actual sell-thru at the point of consumption, whether it’s at a physical store or an ecommerce channel. An accurate and responsive sell-thru forecast ensures that the supply chain is coordinated so that the right item is at the right location, at the right time and in the right quantity.

 

Demand shaping and the merchandising calendar

Omnichannel demand shaping activities such as placement on the web site, free shipping, markdowns, email offers, digital coupons and social media campaigns all help retailers drive sales.

Robust modelling of these demand shaping activities can greatly benefit from ML techniques. Using ML techniques category managers can run “what-ifs” scenarios – looking at the impact of changing the timing and duration of promotions, different product placement strategies on the web site, discounts, or free shipping to review the impact on expected online orders. The expected demand can be broken out by fulfilment method (ship from store, pick up at store, ship from DC) to drive inventory replenishment needed to deliver high customer service.

 

The promise of AI for omnichannel fulfilment

The best supply chain design and robust demand sensing and shaping would be of limited value, if the item the consumer wants is not available, or if an order promised for store pickup is not ready in time. AI and ML techniques can be used to identify the root causes for fulfilment failure, predict which ones are in jeopardy and recommend an action to the appropriate parties so that fulfilment execution is enhanced.

The application of AI/ML enables the retailer to detect shifts in demand signals in time to respond effectively. At the start of the season, merchandisers select products and quantities to order based on recommendations from an AI engine that has knowledge of consumer trends, historical sales, macroeconomic factors, new product attributes and category strategies. Then the planning teams review suggestions the system has made on how to distribute the products across physical stores and online channels, to optimise sell-through and minimise markdowns.

Retailers that are primarily brick-and-mortar today, will need to prepare for the coming step change in consumer preference for omnichannel, and leverage AI systems for supply chain design, demand sensing, demand shaping and fulfilment.