Customer Behaviour Analytics: Billions of Events to one Customer-Product Graph

Speaker: Paul Lam, uSwitch


Graphs, as the data structure, can be used to represent data to bring meaning to massive amount of data. In fact, when viewed in a graphical manner, some problems are naturally easier to solve. One example is customer behaviour analytics. Finding out what differentiate people that viewed item A and purchased A versus those that viewed item A and purchased B is essentially a graphical traversal problem through behavioural relations between people and products.

On the other hand, data are typically generated from events as dimensionless data points. Thus, the technical challenge discussed in this talk is transforming flat data into linked data. Yet, even more exciting is demonstrating the business value by enabling natural customer behavioural querying with limitless data dimensions.

What questions would you ask if you have a Facebook-like graph of what your customer likes, what they bought, and what they viewed? This is what we built at uSwitch by transforming flat data from Hadoop into Neo4J. This talk will walk through how we bridged big data and linked data technologies and the results of such amalgamation.