Sign up for our newsletter
Technology / Data

Creating The Most Sophisticated Recommendations Using Native Graphs

We all appreciate Amazon’s ‘Customers who bought this like you, also bought this’ and

Emil Efrem, CEO, Neo4j

Netflix’s’ ‘Customers who watched this, also watched this’ recommendations. They are invaluable tools; and they have shown us the value of winning customer business by providing the most personalised product and service recommendations possible.

As a result, even the smallest retailer or services company knows that to survive in our increasingly digital world they need to offer equally personalised product and service recommendations to delight and engage the increasingly demanding global customer.

The problem: ‘Customers who bought that also looked at this’ style recommendations may soon be too basic, and stop being of interest to the consumer. Digital consumers now expect personal recommendations based on their individual preferences, history, interests and social context to be taken as read. That raises the bar considerably – maybe too high for many CIOs to reach.

White papers from our partners


eBay’s innovative approach to recommendations

To survive in this more challenging context and meet and surpass your customers’ expectations, retailers and service providers need to offer something much more advanced.

That has to be more along the lines of, ‘You bought this item or service today as well as this last week and the week before, and in last March; you’ve also looked at all these items and services today as well as last week and the week before, and a year ago – so how about this?’ level of suggestion.

The brand needs to provide savvy consumers with intelligent, highly context-sensitive prompts that are able to understand and remember what a shopper is truly seeking to find. However, the reality is that such hyper-personal recommendations can only be generated with the assistance of technology as a way to embed far more intelligence and data-fed capability into your recommendation engine.

AI (Artificial Intelligence) and data-driven, real-time smart software is what is required to do this. And the key enabling backend engine, which will allow these next generation recommendations is graph database technology.

eBay’s AI-based ShopBot is a prime example of why. The online retail giant used graph database to create the service for US customers – a smart, personal shopping ‘bot’ that converses with users via text, voice or photo search capabilities. The application also understands not just shopper text, pictures and speech but also spelling and grammar intention while parsing conversations for meaning and context.

In practice that means for the customer who requests to purchase a pair of gloves costing less than £25, eBay knows what details to ask about next, such as type, style, brand, budget or size. As it accumulates this information by traversing through the graph database, the application is continuously checking inventory for the best match.

eBay’s Chief Product Officer says he turned to graph software because existing product searches and recommendation engines were unable to provide or infer contextual information within a shopping request. Consider the information implied within the phrase, ‘My wife and I are going camping in the Lake District next week, we need a tent.’ Most search engines would just react to the word ‘tent’ – so all that additional context regarding location, temperature, tent size, scenery, etc. is typically lost, though specific information is actually what informs many buying decisions.

Relaying or maintaining this contextual envelope is often a burden left to the user, who has to then to manually sift through search results. Not only does that make shopping a little more of a chore than it needs to be, it means that the user is never presented with options they won’t have consciously chosen: there’s no room for nuance or serendipity – and indeed an opportunity for more sales.

By contrast, eBay’s real-time recommendation engine both understands and learns from the contextual language supplied by the shopper and quickly zeroes in on specific product recommendations. To accomplish this requires a combination of NL (Natural Language) processing, some Machine Learning, predictive modelling – but underscored by a back end graph database.


Why graph software?

That’s a structure, says eBay and other recommendations engine builders, that offers distributed, online real-time storage while scaling to contain their entire product catalogue to store, remember and learn from past interactions with shoppers. It’s also the basis of the system building up its internal profile of the customer and working with that profile as the main way of generating its hyper-personal and relevant suggestions. What’s more, that context is stored, so that ShopBot will recall this information for future interactions.

It’s also exemplary real-time decision making. eBay engineers knew that a chatbot required Internet scale, resiliency and availability so as to deliver usable responses in milliseconds. This led them to use a purpose-built native graph database as it offered exceptional write and read performance. Even with millions of nodes, the application is highly responsive to user requests.

Could eBay have done this using a standard relational database? The traditional way of storing data doesn’t give you much in terms of context and connections. SQL queries are also complicated, and often can’t deliver the information in real time – and for useful recommendations, real-time contextual information has to be accessible.

That’s why relational isn’t the best way to build these hugely sophisticated recommendations engines. The same caveat also applies to Big Data databases, which stumble at managing connections, while these are what graph technology is built to manage.

In sum, to exploit applied AI to deliver the next-generation sophisticated recommendations the market wants – recommendations that will help you up-sell and delight your customers – native graph is the most practical way of getting there.
This article is from the CBROnline archive: some formatting and images may not be present.