For individuals and businesses alike, COVID-19 has had an extraordinary impact. Day-to-day activities which we once took for granted have become alien thanks to the huge disruption we’re experiencing. One of these is the ability to purchase non-essential items in-store, leaving retailers little option but to move the shopping experience online.
Consumer buying habits have become increasingly focused on ecommerce for a few years now. However, the pandemic has certainly seen this process accelerate rapidly. The increase in consumer spending online has continued to prevail even since non-essential stores reopened. In fact, data from the British Retail Consortium showed us that online sales accounted for 40% of total retail sales in July. This is due to the far greater convenience, choice and sense of safety it presents.
To meet the demand of this ‘omnichannel imperative’, retailers will have to redesign their supply chains, as well as focus on demand driven processes to deliver the needs of the new consumer. The question for them is: how do they achieve this?
AI offers one of the most significant ways for retailers to respond to this step change in ecommerce. 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. Essentially it can help retailers manage all aspects of the supply chain design for the digital age, while optimising the online shopping experience for consumers to drive business profitability.
Let’s look at which 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 transportation modes to handle returns
Plan optimal labour requirements at fulfilment centres
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 all channels, and efficiently fulfil the right quantity of products to multiple 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.
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 incremental sales.
Robust modeling of these demand shaping activities can greatly benefit from ML techniques. Using ML techniques category managers can run ‘what-if’ 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 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.
For retailers who are not yet prepared for the omnichannel switch, now is the time to take action. The change is less a matter of if, but when; and for retailers to react effectively, they will need to adopt AI to fulfil effective demand sensing, shaping and fulfilment execution.