How machine learning is changing retail

How machine learning is changing retail

14 October 2016

Machine learning will bring about changes of a similar scale or greater to that seen in the industrial revolution of the nineteenth century. It’s already having an impact on diverse aspects of everyday human life, including the retail industry. But before delving into what this means for our shopping experience, a quick explanation of what we mean by machine learning: Machine learning is a type of artificial intelligence, powered by large-scale data that provides computers with the ability to learn without being explicitly programmed. They can get better over time – the more data and feedback they get. It effectively provides a massively scalable, never tiring, consistent quality digital workforce that can perform tasks we previously thought could only be done by humans.

So where can we see the impact of machine learning?

  • When you are typing a text on your phone or a search term in google, the auto complete and auto correct facilities use machine learning to predict the next word or correct the word you’ve just typed.
  • Your email spam filter determines if an email is spam or if it’s an email you actually want to see.
  • The post office uses handwriting recognition algorithms to determine where each piece of post should be sent to.
  • Google are training driverless cars.
  • Facebook suggests ‘People you may know’.
  • iPhoto detects the faces of your friends and family.
  • Weather forecasting.

Machine learning is ubiquitous, helping our lives become more enabled, more streamlined, more friction-free. Machine learning techniques have been known about for three or four decades but it’s only with the dual advances of fast parallel computing and massive data sets that machine learning has proven its worth.

So how is machine learning changing the face of retail?

Firstly, through enabling retailers to pinpoint critical action areas within an avalanche of possibilities. Secondly, the ability to consume and analyse data that previously had only been considered on a human scale. And thirdly, enabling retailers to look into the future: to plan for scenarios and consider options.

Retailers (like every other sector of business) have never had more data and yet in the future, they will never have so little data. A wealth of data about products, prices, sales performance, costs, availability, logistical activities and consumer behaviour is now available to retailers. The combination of stores’ delivery channels, products, and time-consuming product attributes, creates a vast field of metrics to keep in check - much like an airline cockpit.

Every form of data can be analysed for every category, multiplying again the already vast amount. And with so many data points it’s a seemingly impossible task for even the most experienced retailer to be able to identify key under- and over-performing areas. The use of machine learning in new retail tools now enables this vast field to be examined. Being able to identify, understand and act upon the key contributing factors will revolutionise the ability of companies to drive their business performance.

Machine learning (specifically neural networks) also enables analysis of sources of data not in a structured form - such as customer comments or video data.  Previously these were difficult to analyse beyond the anecdotal. Put simply, these new techniques have opened up a new world that allows retailers to explore data which previously may have been discarded.

Finally, machine learning will impact the ability to predict the future. Through new data science techniques and vast increases in available data, dunnhumby are already helping retail partners simulate scenarios and predict the outcomes. Most retailers are already forecasting to some extent. For instance, they have an idea of the amount of extra product they might expect to sell when a product goes on promotion. Measuring the accuracy of these forecasts is relatively straightforward, facilitating an increase in better predictions, creating a continuous cycle of feedback which powers machine learning algorithms.

Some things are far more complex to predict. Economic, social, legislative and technology changes can have dramatic impacts on customers’ behaviours. For example, the impact of a tax on added sugar in products may well reduce demand due to the change in price, but there may well be other unforeseen changes, such as a change in the acceptance of giving children sugary drinks or the willingness of retailers to stock certain items in certain locations. Tools such as agent-based modelling and reinforcement learning will allow companies to investigate the consequences of their own actions coupled with external forces.

When it comes to the scale of impact machine learning will have on the retail industry, this is really just the tip of the iceberg. But the revolution is here for retailers willing to take the next step with data science.

  Back to all content

Chief Data Scientist