Machine Learning In Retail – A Help Not A Hindrance? 

POSTED BY   Sarah Etling
17th January 2018

Machine learning is often seen as the enemy of the working man, here not only to do our jobs but to do them better than we mere humans ever could. Take the simple self-serve checkout as just one way that machines have sped up the shopping process, leaving no need for the human cashier. And with more shoppers than ever turning to online rather than physical shops, it isn’t looking good for retailers. But incorporating machine learning technology, instead of seeing it as a threat, could be the solution to the current retail crisis.

Machine Learning In Retail: Help or Hindrance?

Using a series of programmed overhead cameras, stores can use vision technology to observe and analyse customer behaviour. Similar to photographic memory, the cameras will capture every movement within the store, and the data can then be used by the staff to create the ultimate shopping experience, giving the consumers exactly what they want from the store. For example, seeing whether customers actually do reach to take products off the top shelf. If they don’t, then the shop can move the products to a lower reach.

The cameras can analyse which products are picked up and viewed by customers but never bought, which direction most consumers walk around the shop and the technology can even analyse which way consumers glance as they are walking around and if they talk to other customers and staff. The shop can then be organised and targeted to suit the consumer perfectly, making a seamless, enjoyable shopping experience. 

One of the pros of online shopping is that when we select one item, the website shows us a full outfit that can be bought to go with the item. FindMine’s machine learning technology looks at a retailer’s entire catalogue. By analysing and categorising the products, it can create outfits that go well with a specific product and can instantly help retailers to put complementary clothing pieces in front of customers, which helps increase additional sales.

Bernd Schoner, co-founder and CEO of DeepMagic, a tech startup that uses machine learning programmes in cameras and computer vision to monitor shopping activities, suggests another way that incorporating the technology could help stores. DeepMagic can flag suspicious behaviour within the store and can provide real-time information to store managers and security staff should a shoplifter or someone with a weapon be detected. This isn’t to get rid of current security staff; the goal is to improve and make the retail experience ‘frictionless’.

Will replacing the human element of shopping with machines push consumers more into online shopping? We enjoy going into the physical shop, we like talking to the cashier and seeing other people as we walk around, but we also enjoy how online shopping is so easily targeted to our needs and wants. Machine learning could change the physical shopping experience, making it exactly what the consumer wants, so we get the best of online shopping, but with the human element that we love. This technology means that staff don’t have to do the tedious jobs like data analysis and can concentrate on the human interaction side of retail which is so important for the perfect shopping experience.


Don’t worry, we’ll never share details with anyone.

Machine Learning In Retail – A Help Not A Hindrance? 

Sarah Etling

Sarah Elting is Head of Marketing at TDMB. Following a degree in Marketing, she headed to Italy to start up a property consultancy. On her return to colder climates, she embarked on a marketing and creative journey that over the course of 12 years evolved from launching paint collections to heading up the marketing of a successful PropTech start-up and becoming CIM qualified. Sarah now writes about all aspects of strategic marketing and technology and continues to be interested in Property.

Get in Touch With Sarah Etling

You may also like

A Cruelty-Free Future With Machine Learning
Machine Learning: The difference between knowledge and understanding
The Sunday AI Review | 18-24th September 2017