Recommendation Engine

Deliver Personalized Recommendations With TigerGraph

Personalized Recommendations Can Significantly Increase Revenues

Every business faces the challenge of maximizing the revenue opportunity from every customer interaction. Companies offering a wide range of products or services face the additional challenge of matching the right product or service based on immediate browsing and search activity along with the historical data for the customer. Recommendation systems are designed to tackle this business need and the impact can be huge: Amazon, whose catalog size is unmatched, reports that 35% of its sales comes from cross-sell and up-sell recommendations.

Additionally, the more personalized the recommendation, the greater the return. 82% of consumers report being influenced by a personalized shopping experience. Purchases with recommendation clicks result in a 10% higher average order value and the per visit spend of a shopper who clicks a recommendation is five times higher.

Legacy Recommendation Systems Are Insufficient for Increasing Revenues

Early recommendation engines, although breakthroughs at the time, simply looked at a couple of connected data points when making recommendations. These recommendation systems perform global statistical computations offline, using snapshots of data that can be days old. They lack real-time modeling and nuanced profiling that is needed today.

Real-time speed is essential. Website visitors have short attention spans: catch them now, or they’re gone. For retailers, their product catalogs can change by the minute. Recommenders need to quickly understand the profile of their client, align that with the rapidly changing profiles of the larger customer base and product catalog, and produce engaging, personalized recommendations.

Why TigerGraph, a Native Parallel Graph Database for Real-time Deep Link Recommendation Engine?

Graph Databases Enable Personalized Recommendations

Using graph analytics for recommendations is the first step towards faster and more personalized recommendations. It’s worth remembering that the standard collaborative filtering algorithm is a 3-hop graph query: (People → who bought the Product ← which You just bought) → also bought these other Products But all graph databases are not created equal. TigerGraph easily handles 3 to 10+ hops, while many others struggle with more than 2 hops. TigerGraph’s deep link analysis lets vendors customize and extend their analytics, enable more hops to collect product features, customer demographics, and the context of the current situation, resulting in more accurate and more personalized recommendations.

For example, It takes two hops to find similar shoppers: Shopper → (Demographics) → Similar Shoppers So demographic-aware collaborative filtering can be implemented in five hops: Shopper → Products purchased → Other Shoppers who purchased the product → Demographics → Other Shoppers that belong to the Demographics → Other Products Purchased. This is illustrated with the example, where Customer 1 has purchased a toy batmobile and light up shoes in prior visits. Customer 2 and Customer 3 have both purchased the batmobile toy, and belong to the demographics of “Suburban affluent parent”. Customer 4 belongs to that demographic as well and has purchased the video game “Super Mario Party for Nintendo Switch”. Based on the five-hop analysis, the video game, “Super Mario Party for Nintendo Switch” is the recommended product for Customer 1.

Graph Databases Enable Real-Time Recommendations

TigerGraph not only delivers personalized results, it does it in real-time. The result is the capture of key “Business Moments”, transient opportunities where people, businesses, data and “things” work together dynamically to create value. TigerGraph lets businesses capture these moments to personalize the customer experience which leads to more transactions.

One of the leaders in ecommerce uses TigerGraph to help drive online, personalized recommendations for its 300 million users. They use TigerGraph to model its catalog of millions of products from thousands of vendors, and its consumer data, including each shopper’s real-time behavior on their website. The result is a better shopping experience with offers that are more likely to result in an initial sale, up-sells, and cross-sells.

Machine Learning Improves the Effectiveness of Personalized Recommendations

Graphs with real-time deep link analytics are also powering the next generation of AI-based recommenders and using machine learning to understand user behavior and preferred actions better than before. Have you ever made a major online purchase, such as a TV or washing machine, and then the recommender asks if you would like to buy a similar product? No. An intelligent recommender would recommend accessories instead.

Similarly, an informed recommender can use the shopper’s browsing behavior to guess at what stage a shopper is at: looking around, evaluating multiple options, price shopping, vacillating, etc. Then the recommender can make an appropriate suggestion to nudge the buyer along.