Will AI And Machine Learning Spell The End Of Retail As We Know It?

Joerg Koesters

According to IDC, artificial intelligence (AI) is expected to become pervasive across customer journeys, supply networks, merchandizing, and marketing and commerce because it provides better insights to optimize retail execution. For example, in the next two years:

  • 40% of digital transformation initiatives will be supported by cognitive computing and AI capabilities to provide critical, on-time insights for new operating and monetization models.
  • 30% of major retailers will adopt a retail omnichannel commerce platform that integrates a data analytics layer that centrally orchestrates omnichannel capabilities.

One thing is clear: New analytic technologies are expected to radically change analytics—and retail—as we know it.

AI and machine learning defined in a retail context

AI is defined broadly as the ability of computers to mimic human thinking and logic. Machine learning is a subset of AI that focuses on how computers can learn from data without being programmed through the use of algorithms that adapt to change; in other words, they can “learn” continuously in response to new data. We’re seeing these breakthroughs now because of massive improvements in hardware (for example, GPUs and multicore processing) that can handle Big Data volumes and run deep learning algorithms needed to analyze and learn from the data. Ivano Ortis, vice president at IDC, recently predicted:

“Artificial intelligence will take analytics to the next level, and will be the foundation for retail innovation, as reported by one out of every two retailers globally. AI enables scale, automation, and unprecedented precision, and will drive customer experience innovation when applied to both hyper micro customer segmentation and contextual interaction.”

Given the capabilities of AI and machine learning, it’s easy to see how they can be powerful tools for retailers. Now computers can read and listen to data, understand and learn from it, and instantly and accurately recommend the next best action without needing to be explicitly programmed. This is a boon for retailers seeking to accurately predict demand, anticipate customer behavior, and optimize and personalize customer experiences. For example, it can be used to automate:

  • Personalized product recommendations based on data about each customer’s unique interests and buying propensity
  • The selection of additional upsell and cross-sell options that drive greater customer value
  • Chat bots that can drive intelligent and meaningful engagement with customers
  • Recommendations on additional services and offerings based on past and current buying data and customer data
  • Planogram analyses, which support in-store merchandizing by telling people what’s missing, comparing sales to shelf space, and accelerating shelf replenishment by automating reorders
  • Pricing engines used to make tailored, situational pricing decisions

Particularly in the U.S., retailers are already able to collect large volumes of transaction-based and behavioral data from their customers. And as data volumes grow and processing power improves, machine learning becomes increasingly applicable in a wider range of retail areas to further optimize business processes and drive more impactful personalized and contextual consumer experiences and products.

The transformation of retail has already begun

The impacts of AI and machine learning are already being felt. For example:

  • Retailers are predicting demand with machine learning in combination with IoT technologies to optimize store businesses and relieve workforces.
  • Advertisements are being personalized based on in-store camera detections and taking over semi-manual “clienteling” tasks of store employees.
  • Retailers can monitor wait times in checkout lines to understand store traffic and merchandising effectiveness at the individual store level—and then tailor assortments and store layouts to maximize basket size, satisfaction and sell through.
  • Systems can now recognize and predict customer behavior and improve employee productivity by turning scheduled tasks into on-demand activities.
  • Camera systems can detect the “fresh” status of perishable products before on-site employees.
  • Brick-and-mortar stores are automating operational tasks, such as setting shelf pricing, determining product assortments and mixes, and optimizing trade promotions.
  • In-store apps can tell how long a customer has been in a certain aisle and deliver targeted offers and recommendations (via his or her mobile device) based on data about data about personal consumption histories and preferences.

A recent McKinsey study provided examples that quantify the potential value of these technologies in transforming how retailers operate and compete. For example:

  • Retailer supply chain operations that have adopted data and analytics have seen up to a 19% increase in operating margin over the last five years. Using data and analytics to improve merchandising including pricing, assortment, and placement optimization is leading to an additional 16% in operating margin improvement.
  • Personalizing advertising is one of the strongest use cases for machine learning today. Additional retail use cases with high potential include optimizing pricing, routing, and scheduling based on real-time data in travel and logistics, as well as optimizing merchandising strategies.

Exploiting the full value of data

Thin margins (especially in the grocery sector) and pressure from industry-leading early adopters such as Amazon and Walmart have created strong incentives to put customer data to work to improve everything from cross-selling additional products to reducing costs throughout the entire value chain.

But McKinsey has assessed that the U.S. retail sector has only realized 30-40% of the potential margin improvements and productivity growth their analysts envisioned in 2011—and a large share of the value of this growth has gone to consumers through lower prices. So thus far, only a fraction of the potential value from AI and machine learning has been realized.

According to Forbes, U.S. retailers have the potential to see a 60%+ increase in net margin and 0.5–1.0% annual productivity growth. But there are major barriers to realizing this value include lack of analytical talent and siloed data within companies.

This is where machine learning and analytics kick in. AI and machine learning can help scale the repetitive analytics tasks required to drive better leverage of the available data. When deployed on a companywide, real-time analytics platform, they can become the single source of truth that all enterprise functions rely on to make better decisions.

How will this change retail analytics?

So how will AI and machine learning change retail analytics, as they are currently defined? We expect that AI and machine learning won’t kill analytics as we know it, but rather give analytics a new and even more impactful role in driving the future of retail. For example, we anticipate that:

  • Retailers will include machine learning algorithms as an additional factor in analyzing and monitoring business outcomes in relation to machine learning algorithms.
  • They will use AI and machine learning to sharpen analytic algorithms, detect more early warning signals, anticipate trends and have accurate answers before competitors do.
  • Analytics will happen in real time and act as the glue between all areas of the business.
  • Analytics will increasingly focus on analyzing manufacturing machine behavior, not just business and consumer behavior.

Ivano Ortis at IDC authored a recent report, “Why Retail Analytics are a Foundation for Retail Profits,” in which he provides further insights on this topic. He notes how retail leaders will use new kinds of analytics to drive greater profitability, further differentiate the customer experience, and compete more effectively:

“In conclusion, commerce and technology will converge, enabling retailers to achieve short-term ROI objectives while discovering untapped demand. But implementing analytics will require coordination across key management roles and business processes up and down each retail organization. Early adopters are realizing demonstrably significant value from their initiatives—double-digit improvements in margins, same-store and ecommerce revenue, inventory positions and sell-through, and core marketing metrics. A huge opportunity awaits.

So how do you see your retail business adopting advanced analytics like AI and machine learning? I encourage you to read IDC’s report in detail, as it provides valuable insights to help you invest in—and apply—new kinds of analytics that will be essential to profitable growth.


About Joerg Koesters

Joerg Koesters is the Head of Retail Marketing and Communication at SAP. He is a Technology Marketing executive with 20 years of experience in Marketing, Sales and Consulting, Joerg has deep knowledge in retail and consumer products having worked both in the industry and in the technology sector.