Deliver Personalized Recommendations With TigerGraph
Portion of Amazon’s revenue from cross-sell & up-sell
Per visit spend of a shopper who clicks a recommendation
Size of global recommendation engine market in 2022
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, with its unmatched catalog size, 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 the real-time modeling and nuanced profiling 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 their client’s profile, align that with the rapidly changing profiles of the larger customer base and product catalog, and produce engaging, personalized recommendations.
Database for Product + Service Marketing?
Why TigerGraph, a Native Parallel Graph Database, To Build a Real-time Deep Link Recommendation Engine?
Uncovering referral relationships is a lot easier with TigerGraph. Consider the example, where Dr. Douglas Thomas, a general practitioner sees a patient, p1003 on September 8, 2017, for shortness of breath, resulting in the claim c10005. The same patient, p1003 sees Dr. Helen Su, an interventional cardiologist (surgeon) on September 20 for cardiac catheterization (claim c10030) and again on September 23 for the angioplasty operation (claim c10031).
TigerGraph displays all of these claims connected to patients and prescribers in GraphStudio, enabling data analysts to understand the relationship intuitively. TigerGraph also links them based on a time window to deduce referral relationships. In this example, the claims occurring within four weeks are considered for establishing a referral relationship. It takes four hops or steps for traversing from the referring physician, Dr. Douglas Thomas to the referred physician, Dr. Helen Su via relevant claims identifying three common patients, p1003, p1004 and p1005 over the month of August and September. A referral edge or relationship is established between Dr. Douglas Thomas and Dr. Helen Su and the relationship edge carries important information such as the number of patients referred, healthcare condition groups related to the referred patients. The prescription claim data can be added in, to provide specific drugs for cardiac care that are frequently prescribed by both physicians.
Armed with these insights, pharmaceutical companies producing the cardiac care medication and the medical equipment manufacturers producing stents and other products for the cardiac surgery can market those products to Dr. Douglas Thomas and his referral network including Dr. Helen Su in the San Jose area.
Read More
Graph Databases Enable Real-Time Recommendations
TigerGraph not only delivers personalized results, but it also 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, leading to more transactions.
One eCommerce leader uses TigerGraph to help drive online, personalized recommendations for its 300 million users. It uses 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 its 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.
FAQ
A recommendation engine is a system that suggests relevant products, services, content, or actions based on customer behavior, preferences, and connected data. It is important because personalized recommendations help businesses increase engagement, improve customer experience, drive cross-sell and up-sell opportunities, and maximize revenue from every customer interaction.
Graph databases improve recommendation engines by modeling relationships between customers, products, services, behaviors, preferences, and transactions. Unlike traditional systems that rely on static profiles or offline snapshots, graph databases can analyze real-time connections across multiple hops to identify what customers are most likely to need, want, or purchase next.
TigerGraph enables real-time, deep link recommendation engines that analyze massive connected datasets at enterprise scale. It can combine historical customer behavior, real-time browsing activity, product catalogs, peer similarities, and contextual relationships to deliver more relevant recommendations when the customer is ready to act.
Yes. TigerGraph supports real-time personalized recommendations by continuously analyzing current customer behavior, changing product catalogs, and connected activity across the broader customer network. This enables businesses to capture high-value business moments with timely, relevant recommendations that improve engagement, conversion, cross-sell, and up-sell performance.
Machine learning improves graph-powered recommendations by learning patterns across customer journeys, product relationships, purchase behavior, and preferred actions. When combined with TigerGraph’s real-time graph analytics, machine learning models can better understand context, predict intent, and recommend the next best product, service, offer, or action.
Legacy recommendation systems often rely on offline processing, stale data snapshots, shallow customer profiles, and limited relationship context. They struggle to respond to real-time behavior, changing inventory, complex customer journeys, and nuanced purchase intent. A graph database addresses these challenges by analyzing connected data directly and in real time.
TigerGraph helps businesses increase revenue by delivering more relevant recommendations at the moment customers are most likely to engage. By connecting customer behavior, product relationships, peer patterns, and real-time activity, TigerGraph helps improve personalization, increase conversion, drive larger orders, and create more effective cross-sell and up-sell opportunities.
