Taking AI in Retail to the Next Level

Most online retailers recognize the importance of artificial intelligence and machine learning technologies. In fact, more than four-fifths of e-commerce businesses report that they're either exploring or already using AI solutions to increase business success.

Whether these companies use AI to maximum effect, however, depends on exactly how they integrate AI into their operations. Leveraging AI to address basic needs through techniques like simple clickstream analytics isn't enough on its own to maximize conversion rates and revenue.

That's why retailers that want to take full advantage of AI should be thinking beyond simple AI use cases in e-commerce. Those use cases are one step toward success, but they're not the full story.

Allow me to explain by discussing common use cases for AI in e-commerce and differentiating basic from more advanced ones.

AI in Retail: Simple Examples

Let's start with relatively simple examples of how online retailers can use AI — or something approaching AI — to enhance their business.

One of the simplest use cases to consider in this regard is clickstream analytics. Clickstream analytics allows retailers to track user activity on their websites — e.g., which items users click on most frequently and which pages they navigate through on their way to making a purchase. By employing algorithms to analyze this data in the aggregate, retailers can establish a baseline of customer behavior. They can also identify opportunities to increase customer satisfaction and conversion by, for example, placing items that customers click on more frequently at the top of search results.

Insights like these are good. However, for many e-commerce businesses they're not enough to achieve true sales optimization. Data points like which products site visitors click on most often aren't sufficient on their own to solve questions like which products will drive the highest revenue, because these limited data points don't take into account factors such as whether items are actually in inventory or what the margin is on the items. They're just a blunt — and relatively imprecise — measure of which products are most likely to draw clicks.

A slightly more complex, but still basic, example of how e-commerce businesses can use AI is customizing facets within website navigation. Facets help site visitors filter products that appear within search results based on factors like product color or size. Using AI, businesses can identify which facets are most popular among customers and prioritize them within navigation menus.

AI-driven facet customization is a useful way to help optimize the customer experience and, in turn, increase conversion rates. But here again, this is a basic use case for AI that leads to limited value. The signals that drive facet customization are restricted to data points like how often visitors use different facets, which optimizes only one specific part of the customer journey — and which does it based on generic, one-dimensional data.

Advanced Uses for AI in Retail

What can e-commerce businesses do to take AI to the next level? The answer involves two key pillars.

The first is collecting a multitude of data points that help businesses understand customer needs and align them with business priorities in a holistic way. This data might include basic information, like the kind that drives clickstream analytics, but it should also include data like product ratings and reviews, product inventory status, product shipping time, and perhaps even data points that reflect how close the retailer's relationship is to different product vendors.

The second essential ingredient in advanced AI for retail is algorithms that can dynamically rank search results using the multifaceted data described above. Dynamic ranking is essential not just because it ensures that rankings can constantly evolve along with continuously changing data, but also that search results can be truly customized and personalized for each customer. In turn, businesses are able to achieve higher conversion rates than they would through a blunter approach wherein product search results, displays and navigation are optimized for customers in general, not personalized for individuals.

Of course, it's important while using AI-powered optimizations to give merchandisers control over the product search results delivered by sophisticated AI. For example, if your business wants to prioritize one vendor's products, that policy should inform search results to ensure the products rank highly — even if other data would suggest that they should receive less priority.

This is the approach that e-commerce businesses at the forefront of the AI revolution are using to get the very most out of AI and ML as solutions for optimizing online shopping and maximizing revenue. They also take advantage of more basic AI-based techniques, like clickstream analytics, but they realize that those strategies are only the tip of the iceberg when it comes to AI in retail.

Conclusion

Going forward, adopting basic AI will no longer be enough to ensure e-commerce business success. In a world where most retailers are already using some type of AI, companies seeking to lead need to adopt advanced AI-based techniques that allow them to leverage all data at their disposal to create the most engaging, dynamic and personalized shopping experience possible, while also aligning that experience with business priorities.

Keith Mericle is the CEO of Innovent Solutions, a company that provides provides consulting, training, support and solutions for Search, Business Intelligence and eCommerce technologies.