Uncover Hidden Ecommerce and Market Gems with Knowledge Graphs

0

Article by Neo4j APAC Vice President of Marketing, Daniel Ng.

Marketers have access to more data than ever before – and it’s growing exponentially. The acceleration of digitalization caused by the pandemic has created vast repositories of data on consumers, products and purchases. According to Statista, global data creation – the total amount of data created, captured, copied and consumed – is expected to reach over 180 zettabytes by 2025 worldwide.

The challenge is knowing how to sift through and identify trends and patterns that can be used to generate valuable insights. As a massive stream of data, it has little to no value to marketers without context or relevance. How can marketers transform information domains and make data meaningful and useful?

The power of knowledge graphs

In today’s data-rich world, marketers can convert data into greater marketing intelligence with knowledge graphs. Unlike a traditional database in the form of a table, with rows and columns of data, knowledge graphs store data as linked nodes and the relationships between them. This data can then be displayed visually, in colors and shapes, making it easier to spot patterns and anomalies.

For example, in an Excel spreadsheet, you can quite easily connect one set of data (customers) to another (their purchase history). But trying to add additional context such as demographic information, path to purchase, time and date of purchase, and weather conditions in a locality is difficult, unwieldy, and impossible to do in a single sheet. However, this context can be critical in spotting patterns of who is buying what, when, and how.

Knowledge graphs are designed to uncover information about customer needs, products, and market trends, mitigating the challenges of constantly growing and highly interconnected data sets. They excel at connecting and managing masses of shopper and product data to answer complex queries.

Marketing Effectiveness Analysis

For example, suppose we wanted to analyze website activity and track how people find different pages on a website: for example, by clicking on an advertisement, through a search engine, from social media or in an email link. This will help us understand if an ongoing marketing campaign is effective and better understand the behavior of site visitors who become customers.

In a knowledge graph, all pages and all marketing channels become nodes linked to each other. By adding context to links (relationships), we can start making complex queries. For example, if we have data on visit times, we can analyze the evolution of the performance of individual marketing channels and the interest for specific pages. Then, by adding visitor location data, we can analyze whether certain channels work better for certain geographic markets.

Real-time recommendations

Real-time recommendation engines are essential for online retailers. The goal is to surface relevant product suggestions and prompt shoppers to add last-minute extras to an online shopping cart. This benefits both parties: the seller can offer high-margin items, overstocks, and promotions, while the buyer discovers useful and relevant items, improving their customer experience.

Generating relevant recommendations involves instantly correlating data on products, customers, inventory, suppliers, logistics, and even social sentiment, as well as instantly capturing any new interest shown during the customer’s current visit. Sifting through all of this data in real time is beyond the capabilities of a conventional relational database. However, matching historical and session data is trivial for a knowledge graph.

A knowledge graph can also use and weight multiple recommendation methods, such as recommendation based on users or similar products, user history and profile, or business strategy (promotions, margin, inventory) .

Know your customers

In the post-cookie world, knowledge graphs provide a way to connect massive amounts of shopper and product data to generate insights into product trends and customer needs. Knowledge graphs are much faster at doing this than traditional means. They can be used to analyze web traffic and clickstream data and create unique customer profiles.

American media conglomerate Meredith Corporation has used graph algorithms to turn billions of page views into millions of pseudonymous IDs with rich browsing profiles. It then consolidated 350 million profiles that would have been considered unique individuals with different interests and patterns into 163 million richer and more accurate profiles. This gave him a better understanding of customers and the market.

Gartner predicts that by 2025, graphics technologies will be used in 80% of data and analytics innovations, up from 10% this year. Ultimately, knowledge graphs enable marketers to achieve their goals and drive competitive advantage and overall business success.

Share.

Comments are closed.