Using Artificial Intelligence to Uncover Revenue Opportunities in the Off-Season

Press enter to search
Close search
Open Menu

Using Artificial Intelligence to Uncover Revenue Opportunities in the Off-Season

By Sean Byrnes - 09/13/2019

Seasonality is a critical part of planning for retailers. You might increase inventory based on a holiday or back-to-school time or you might change merchandise to favor cold-weather gear in regions expecting chillier temperatures. Most retailers use historical purchase and shopper demand data to plan for seasonality with the belief that seasonality always follows the seasons.

But what happens when consumer behavior doesn’t perform as expected? For example, you increase your selection of trendy fall boots starting in August, but shopper demand actually started in late June. This missed off-season opportunity can have huge ramifications on revenue generation, customer experience and loyalty.

One Day Can Make a Difference

Even retailers tracking real-time shopper behavior can easily miss opportunities. The problem isn’t the data itself, it’s the overwhelming amount of data there is to analyze.

Tracking page views on a retail e-commerce website is a good example. Traditional web analytics and reports (even real-time reports and business intelligence dashboards) typically show consumer traffic data over a period of time. It’s easy to see which pages have more traffic than others.

But what the reports don’t show is whether or not the traffic data falls within normal consumer behavior expectations. It doesn’t tell us if there’s an opportunity or a problem that needs to be addressed. Additionally, consider all the data points you’d want to analyze to track consumer trends, including page views, abandoned carts, each product SKU, etc. It quickly becomes thousands of data points to track.

When we apply artificial intelligence (AI), we open up a whole new world of opportunities. AI can use historical data to create a model of “normal” data behavior. Then, when consumer behaviors fall outside the expected range of behaviors during daily monitoring, retailers can see this change and act on it. This is typical anomaly reporting.

Today, we can even go one step further. The latest wave of AI analyzes thousands of insights and illuminates the changes that matter most, including problems with inventory or a break down in the supply chain. It can uncover the impact of marketing efforts on cart abandonment, identify broken e-commerce processes or point to poor product placement.

By flagging just a handful of the most important changes, retailers have an almost immediate opportunity to take advantage of positive behaviors or alleviate problems that may be eroding sales. This new wave of AI empowers retailers to make better business decisions faster instead of bogging them down with too many, or vague, insights.

Automated Business Analysis Does the Work for You

The idea that retailers can automatically analyze data and receive daily alerts with four to five stories showcasing important data changes is called automated business analysis. It’s an ongoing strategy of analyzing data that elevates and proactively reports on the unexpected. This is critical for retailers that want to get ahead of changes in consumer behavior, competitive tactics and other business trends that they don’t know to track. Automated business analysis doesn’t need to be told what to look for. It just looks for changes outside the normal range.

An automated business analysis approach offers personalized insights each morning to retail leaders and managers based on data from the last 24 hours, highlighting exactly where they should be looking and what they should be looking for within the data.

This approach delivers a couple of important benefits. First, it adds context and timeliness to insights by delivering, proactively, only the insights that indicate some level of unpredicted change. It points to something specific that needs further review. Second, the reports drive the day’s action items in a way that allows retailers to address activity and adjust quickly, shortening the time-to-action.

Acting on Unexpected Consumer Behavior Leads to a 30% Sales Uptick

One great example of this approach is Jack Rogers, a digital-first footwear and accessories retailer with select brick and mortar stores. While the nearly 60-year old brand knows its customers’ general demand for different product categories, managers also wanted to have better insight into changing preferences in order to optimize marketing spend. To do this, they needed to see how behavior changed daily and looked year-over-year for opportunities to accelerate sales. It turns out they only had to look at one campaign, at just the right time, to make a difference.  

According to Jack Rogers, the company has a small digital analytics team, but a lot of data. Its e-commerce team was using Google and Facebook for paid promotions, so they applied Outlier’s automated business analysis platform to analyze and alert on the consolidated paid advertising data.

Jack Rogers’ goal was to have the platform analyze its Google Analytics and Facebook Ads data on an automatic, ongoing basis, with the intent of leading managers to new insights that might help them with marketing.

Simply using its advertising source data, Outlier identified that product interest had unexpectedly increased for a specific segment of footwear in February, but checkouts had not increased for the same product segment. Having an automated business analysis platform flag the data behavior change enabled the team to modify its marketing activities and spend within 24 hours. They were able to very quickly promote the category to females in the Southeast that were trending upward and capture new sales.

The unexpected jump in interest was much earlier in the season than Jack Rogers had anticipated. But by taking fast action and modifying email marketing campaigns immediately to take advantage of the interest, the company ultimately achieved a 30% sales increase year-over-year.

For Jack Rogers, automated business analysis gave the retailer immediate visibility into unexpected changes in customer shopping patterns and allowed them to identify and target these shoppers with marketing programs (online and offline) in order to drive more sales.

Seasonality will continue to impact how retailers do business, but it’s also important to understand behavior changes as they happen. While there are lots of tools available for historical reporting and general dashboards, only automated business analysis platforms have the power to direct immediate operational adjustments, meaning brands can understand, evaluate and change behaviors just as quickly as consumers.

-Sean Byrnes, CEO, Outlier