The way consumers shop, think and behave is changing more quickly than ever and this is largely down to the advances of technology that dovetail into our everyday lives. With these sea changes in consumer behaviour it is crucial that organisations stay one step ahead by pulling disparate sources of big data together and predicting what their customers will do next.
Breaking down the barriers to real time insight
Many organisations are still siloed which means bringing together a comprehensive view of your customer can be difficult. The technology department, research team, data analysts and marketing each have their own systems, different methodologies and are collecting different data in different formats. Until now, and the advances in technology, it has been too complex to bring this disparate data together and the silos have remained in place.
GDPR has also had an impact. No longer can organisations collect, store and process their customers’ data in the ways they have done before resulting in databases that are laden with gaps. To plug these holes, businesses are increasingly using online data, however with the advent of significant changes to ePrivacy this practice will likely be curtailed, and customer data will become even more fragmented making the job of gaining one consistent view of the customer even harder.
A new approach to segmentation using deep learning
The answer lies in a new approach to segmentation. One that has been built for the modern world that answers the questions that businesses might not even know existed. We refer to it as ‘deep learning segmentation’ which is proving to be a successful way to break through the barriers we’ve identified and realise the opportunities that big data affords.
Traditional data analytics are based on linear patterns and testing hypotheses. But today there are far more predictive and insightful patterns to be found that lie outside of the linear. A good example of this is in the prediction of a home move. The linear approach says that when a household applies for planning permission they will be staying put. Instead of moving they are concentrating on home improvement. However, if you look at older residents that live in coastal communities the application for planning denotes the total opposite. AI has identified a pattern that says when people in this specific group of householders apply for planning permission, they will move house. This is because they will be selling their prime location property to a developer who will be building top spec homes that are currently in demand in areas such as Sandbanks and Harbour Heights in Dorset.
Predicting consumer behaviour
Traditional segmentations have been used to find the answers to many different problems including customer retention or the impact of the weather on purchases. But an issue that many marketers have come up against is that the more generic the segmentation the less predictive it is of specific behaviours. This is one of the key benefits of deep learning segmentation. It builds up layers of insight to provide a more holistic and accurate picture of the customer. It does this by bringing together the disparate data. Stable data, including property information and demographics can be layered alongside more transient data such as clicks and likes to provide a dynamic customer view, but within a context provided by transactional data and trend data over time.
Ultimately, deep learning segmentation fills the gaps in databases and unifies the different datasets. In doing so it breaks down the silos within organisations and provides a common language to describe the customer which can be used by everyone in the business and a greater understanding of the customer base across every level. These segmentations can be built very quickly – in a matter of hours not months, providing access for the first time to real time customer insight.