Maximising The Effectiveness Of Your Campaigns With Machine Learning

While most businesses recognise the power of big data and analytics, few have yet to unlock the true potential of data through machine learning, writes Zendesk data scientist Dr Chris Hausler (pictured below).

Marketers have known that the foundation of customer loyalty is strong relationships. In the early days, building these relationships meant face-to-face interactions and phone calls.

Today, the rise of e-commerce, multiple communication channels and the proliferation of mobile devices has meant that consumer behaviour has significantly shifted. We now demand access to immediate information and want our issues to be solved instantly at the click of a button.

Understanding big data and analytics

While consumers have been busy adapting to technological change at an exponential rate, they have also been happy to share more and more information. As a result, marketers are now tracking a customer’s engagement history with their brand through a range of data sources such as social media, purchase history and customer support tickets.

However, while most businesses recognise the power of big data and analytics, few have yet to unlock the true potential of data through machine learning.

The shift towards personalisation

In the past, marketers would use a ‘batch and blast’ approach for email and direct mail campaigns to reach potential buyers. But today, more marketers are personalising content for their customers, and this requires sophisticated machine learning technologies, more broadly referred to as predictive analytics.

Advances in machine learning automatically surface patterns and actionable insights from vast data sets – and do so in real time. This has made it easy for marketers to react quickly to a wide range of customer behaviours on a massive scale. By delivering immediate advice on the best way to engage or follow up with a customer, machine learning is powering a new level personalised service.

Predicting customer behaviour

Machine learning technologies can combine basic customer demographic and purchase data with behavioural cues like email or website interactions, or how discounts affect buying patterns, to offer much deeper insight into consumers’ true intent. ‘Clustering’ and ‘propensity’ models can be used to determine how likely different customers are to actually make a purchase at any given time. ‘Collaborative’ filtering models can help marketers predict what products or services customers are most likely to buy based mainly on what other customers (with similar traits) have bought together in the past. Amazon of course has made this type of model ubiquitous with its “people who bought this product also bought…” recommendations.

Indeed, in the next 10 years we could see machine learning systems capable of understanding the nuances of human language. Yann LeCun, who leads Facebook AI Research, recently said: “We might see the emergence of considerably more intelligent AI agents for dialog systems, question-answering, adaptive robot control, and even planning.”

Beware the creepy factor

A few words of caution though when using machine learning and predictive analytics for your marketing campaigns. It’s always important for you to tell your customers what data you are collecting and why.

Don’t hide opt-ins and unsubscribes in the tiniest print somewhere at the bottom of a registration form or email. If this means capturing a little less data than before, so be it. But do use the data you have intelligently. Marketers should always focus on how to use data to improve the customer’s experience, not just the company’s bottom line.

Brands need to allow customers to edit their data, as well as explain why their algorithms are making specific recommendations and allow customers to give feedback on whether the recommendation was helpful or relevant.

Marketers need to find new ways to cater to a constantly changing audience. It’s clear that we are facing a new revolution in the way that businesses serve their customers, as technological advancements make it possible to replace humans with intelligent algorithms. The scale of the change happening makes machine learning a priority not only for global businesses such as Netflix, Facebook and Google, but for all businesses.