It is widely acknowledged that uncertainty resulting from the pandemic created many opportunities for grocers but reduced demand in the fashion and apparel industry. In the meantime, customer preferences and shopping behavior keep changing, impacting the entire retail supply chain industry.
A digital transformation of supply chain processes is key in maintaining margins and service amidst these changes so that retailers can quickly analyze, optimize, and evaluate complex decisions before taking action. Technologies like Artificial Intelligence (AI) and Machine Learning (ML) have had increasing success in driving profitable growth in many retail sectors. In most retail applications, AI and ML are running in the background and helping company operations run more smoothly and ultimately driving the company’s digital transformation. Examples of AI in retail settings can include ‘next-best-offer’ options for retail shoppers, or the use of external data to create accurate forecasts.
Retailers can also leverage AI and ML technologies to build a more robust supply chain network. For example, by incorporating external data points into their forecasting models to proactively respond to material shortages, sudden surges in product demand, or changes in consumer purchasing behaviors (i.e. pivoting from in-store purchases to online during COVID lockdowns).
Below are insights on how retailers can benefit from AI across demand sensing, demand shaping and demand response.
How retailers can leverage AI to build resilient supply chains
Retailers are in an environment of increased demand volatility due to rapidly changing assortments, shorter product life cycles, increased promotional activity, social media influencers that go viral with products, and order volatility due to eCommerce. As a result, it is becoming more difficult to predict where demand will occur—across both brick-and-mortar and omnichannel—and to efficiently source and fulfill the right quantity of products to thousands and even millions of locations.
To be able to quickly respond to changing consumer buying patterns, forecasting techniques that leverage demand sensing capabilities are a necessity. Demand sensing focuses on eliminating supply chain lags by continuously learning and reducing the time between demand signals including order frequency, order size, local events, and the response to those signals.
New ML mathematical techniques enable demand sensing with pattern recognition and the ability to overcome latency issues associated with traditional time-series statistical methods. These new algorithms improve the accuracy of forecasts across all channels by leveraging internal drivers as well as external factors to build real-time data signals.
Retailers devote a large number of resources trying to shape demand through promotions and campaigns at both the store and online channels. They resort to various in-store promotions with temporary price discounts, displays, and feature inserts in local publications. There are also omnichannel demand shaping activities such as placement on the website, special offers like free shipping, and digital coupons which drive incremental sales.
Robust modeling of these demand shaping activities can greatly benefit from ML techniques. Category managers can run ‘what-if’ scenarios, look at the impact of changing the timing and duration of promotions, try different product placement strategies on the feature insert or website to understand the impact of in-store sales or online orders. The expected demand can be broken out by fulfillment method (in-store sales, ship from store, pick up at store, ship from DC) to drive the inventory replenishment needed to meet customer expectations.
Responding to Demand
Even with accurate forecasting taking into account internal and external drivers, and robust modeling of demand shaping, retailers will still encounter out-of-stocks and inventory in the wrong locations, leading to expedites and unnecessary transfer costs. AI/ML techniques can optimize product availability, by anticipating customer fulfillment issues in advance and by making prescriptive recommendations to take actions to mitigate poor customer service.
This requires end-to-end visibility with a digital twin, which is a digital representation of the physical supply chain, where every asset is represented with its capacities and connections and is available to be analyzed in real time, to determine the next best action when exception conditions are detected.
With the application of AI/ML techniques on the underlying digital twin, retailers can evaluate trade-offs between demand, sourcing, transportation, flow path alternatives, inventory, and service in a holistic fashion.
Leveraging Retailer Data Science Teams
Many retailers have data science teams that have developed cutting-edge algorithms in critical areas such as store and omnichannel forecasting, labor capacity planning, assortment optimization, promotion and price modeling and out-of-stock analysis. However, a significant portion of these efforts never end up being fully deployed. Deploying AI/ML projects into usable applications remains a principal barrier to delivering business value.
A key competitive advantage for retailers is the ability to efficiently turn their algorithms and models into production-grade deployed applications.
This platform should contain a robust digital twin with current master data such as items, locations, capacities, suppliers and policies, as well as transactional data on sell-thru, store orders, inventory, in-transit and supplier orders. The platform should also support enhanced cross-functional coordination with role-based access, scenario management, workflows, and flexible reporting capabilities. To build a stronger demand planning and forecasting strategy, a retailer’s data science team will be a key component because the team not only understands the technology capabilities, but also understands your business goals and needs as well.
Technology and automation will continue to play a big role in the transformation of retail with a relentless focus on supply chain design, localized assortments, anticipating consumer demand, shaping consumer purchases with pricing and promotions, and fulfilling demand across all channels in the most cost-effective manner.