Retail and services industry need to massively up their personalisation game in 2018, warns graph database pioneer Emil Eifrem

Quite rightly, retailers are continually looking to help shoppers search for the items they seek. The problem is doing it in a way that is at least as good as the way the world’s favourite store, Amazon, does.

Amazon introduced us to the ‘Customers who bought that, also looked at this’ style of shopping a decade or more ago – and ever since, competitors have been looking to improve personalised recommendations’ sophistication in order to meet and surpass expectations.

The market wants to provide consumers with intelligent, highly context-sensitive prompts. However, such hyper-personal recommendations can only be generated with the assistance of technology – as that’s the only way to embed more intelligence into a recommendation engine.

AI (Artificial Intelligence) and data-driven, real-time smart software is what is required. And with the key enabling tool that will allow such Next Generation recommendations being graph database technology.

For example, eBay’s AI-based ShopBot, a prime instance of the type of graph-powered hyper-personalisation that brands need to offer, uses the approach. As eBay’s Chief Product Officer has said, existing product searches and recommendation engines were unable to provide or infer contextual information within a shopping request.

Traditional search is getting too limited

Take the example of what’s implied within the phrase, “My wife and I are going camping in Lake Tahoe next week; we need a tent.” Most search engines would just pick up on the word “tent”, so the additional context regarding location, temperature, tent size, scenery, etc. is typically lost.

Yet it’s this type of specific information that informs many buying decisions. Relaying or maintaining this context is a burden often left to the user, and a solution is needed to remove the hard work associated with shopping.

The solution ShopBot uses is a combination of ML (Machine Learning), accurate predictive analytics, a distributed, real-time storage and processing engine, backed with NLP (Natural Language Processing). But it also uses a graph database to process all the real-time data connections required. That’s because graph technology helps to refine the search against inventory with context – a way of representing connections inside your data sources, based on shopper intent. This allows the system to build up its internal profile of the customer and working with that portrait is the main way of generating its hyper-personal and relevant suggestions.

Store and build deeper customer ‘portraits’

Even better, all that contextual information gets stored, so that ShopBot can recall this information for future interactions. When a shopper searches for “brown bags” for example, ShopBot knows what details to ask about next, such as type, style, brand, budget or size. And as it accumulates this information by traversing through the graph database, the application is continuously checking inventory to identify specific product recommendations – a great example of real-time decision making.

Without graph software at the centre, you can’t easily offer consumers these hyper-personalised hints. The traditional way of storing data is ‘store and retrieve’, but that doesn’t give you the context and connections. SQL queries are complicated, and also can’t deliver the information in real time – and for customer search to deliver useful recommendations, real-time contextual information has to be fast to work.

Tapping into human interest and delivering highly responsive, accurate help is what hyper-personalised recommendation engines have to look like – and what savvy consumers are demanding.

And it really looks like AI working in lockstep with native graph is our best way of getting there.

Emil Eifrem

Emil Eifrem

Contributor


Emil Eifrem, CEO, Neo4j