Were you unable to attend Transform 2022? Check out all of the summit sessions in our on-demand library now! Watch here.

Artificial intelligence has been shaking up the marketing world for the last few years, helping automate menial, repetitive tasks, inform better creative decisions, and predict revenue projections.

But many of the tools available for that latter category, namely, predictive analytics, have a less-than-stellar accuracy rate.

South Africa-based Xineoh has developed a platform for predicting customer behavior with AI. The company claims its technolgoy is more accurate than any other solution available.

Xineoh was founded in 2010 and raised $2 million from U.S. and Canadian investors in June 2017. While accurate AI-powered predictive analytics is not a new thing, it is mostly only affordable at a corporate and enterprise level. Xineoh is different because it targets small to medium-sized businesses.


MetaBeat 2022

MetaBeat will bring together thought leaders to give guidance on how metaverse technology will transform the way all industries communicate and do business on October 4 in San Francisco, CA.

Register Here

So what can it do?

The platform’s deep learning capability matches individuals with products, inventory with business opportunities, prices with spending propensities, and people with usage patterns. And it does this exceptionally quickly.

“Xineoh has built an extremely efficient Deep Belief Network that can train huge amounts of data in minutes,” Xineoh CEO Vian Chinner told me. “So to be technically specific, we use a Deep Belief Network, but it is a combination of machine learning and AI.”

In other words, the system works like many predictive analytics solutions in that it finds patterns in historical data through machine learning and then applies those patterns to current data to predict the future. It just does it very quickly.

“Something to consider is that a business is a chaos system, and as predictions are implemented in decisions, the chaos system reaches a new equilibrium that may alter patterns,” Chinner said. “Netflix is a good example. Initially, a large portion of their customers visited with a specific video in mind that they wanted to watch. If a streaming provider wants to satisfy this need best, they would need to have a large selection of videos, starting with the most popular items. They realized … that if they simply held the items that are most relevant to each customer, they needed only a quarter of the expected items in inventory, leading to large savings.”

That mechanism changed the way people use the streaming giant’s platform.

“People started using Netflix differently and started using it with a specific amount of leisure time in mind, as opposed to watching a specific video,” Chinner said. “This went one step further with Netflix then starting … to produce the videos most relevant to their different users. This made their business model much more sticky because they now have unique needed content not available elsewhere.”

Xineoh’s data is able to provide insights that can help other businesses transform similarly.

Essentially, it can do this by predicting what consumers will buy, where to market products, and how to target a brand’s story. By anticipating what products consumers will buy with a high level of accuracy, Xineoh allows the business to minimize unnecessary inventory and maximize working capital.

It also helps match customers with the right products and services, predict churn, and inform marketers of the best time to reach out to customers to reduce cancellations.

“We are working with a couple of clients on optimizing their pricing models,” Chinner said. “Many businesses need price discrimination to optimize profit, as well as lifetime customer value. There are many variables that determine the optimal pricing, and businesses are looking for smart tools to augment the ability of their sales teams to decide what prices to quote which customers at what times.”

And how do those projections affect the bottom line?

“We are seeing great results,” Chinner said. “For one business, the estimated gain in lifetime customer value, using our solution, will be around 21 percent.”

It’s the accuracy of the Xineoh solution that stands out the most, however. After all, predictive analytics using AI has been around for some time.

In a study completed in-house, the algorithm’s ability to predict which movies viewers would watch was tested on the MovieLens database, which contains 20 million movie ratings.

Above: The X-axis represents recall accuracy, and the Y-axis contains the popularity bias.

“On the engineering side, we are continuing to improve the prediction results at a massive rate,” Chinner said. “We can currently out-predict our closest competitor at double their accuracy.”

Xineoh is expecting to raise another round of funding before the end of the year to further improve its technology.

VentureBeat's mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.