The grocery retail sector has a growing reputation for innovation, with retailers increasingly working to harness the rewards available from social media. Social platforms are now widely used by retailers in an effort to connect with customers in an engaging and authentic manner.
Decision-makers are now able to interrogate masses of data gathered from interactions on social media to understand what people really think about issues such as product recipes, store layout and customer service, enabling them to make changes to reflect the expectations of their customers.
In particular, grocery retailers can gain additional value by using social media tools to quickly understand which products and services are performing well and where adjustments can be made to boost performance.
Something that all companies struggle to deal with is the sheer volume of information that there is to process. This is where analytics tools prove invaluable.
The tools that are already available struggle with analysing sentiment. They are able to determine basic feedback, ‘this is good’ or ‘this is bad’, for example, but they cannot harness further insight from each post.
S4RB has recently partnered with Warwick Analytics, a machine learning software developer and provider to bring PrediCX to grocery retailers. This platform uses Optimised Learning Technology to ensure the highest accuracy possible when labelling concepts or keywords pulled from social media.
Because this tool has been created specifically for the grocery retail market, it is able to accurately determine the root causes for dropped baskets; churn from particular stores, products or grocery brands; recommendations for future products, packaging, recipes and store layout; and early warning of previously unforeseen quality issues.
The addition of PrediCX to S4RB’s Affinity™ platform allows retailers to learn not just how many people are talking about their brand, but also to automatically identify the intent of the customer towards the brand and to automatically associate this intent with not just the shopping experience, but also with product feedback.
For example, if customers tweeted feedback about how a product’s recipe did not correlate to the messaging on the packaging, traditional social media insights would flag this as a product fault and, if enough negative feedback was recorded, the product could be liable to be discontinued.
However, by harnessing detailed insight beyond sentiment and into customer intent, retailers are able to see that the error was related to the packaging - a relatively straightforward fix compared to undoing the whole product development cycle.
Human behaviours, like sarcasm, can lead to the intent of a comment being misconstrued with most tools. Based on human analysis of a small section of data, this new technology understands concepts rather than keywords and therefore identifies intent to a far higher accuracy than has been possible until now.
Rather than just determining the sentiment of the comment (positive vs negative), the PrediCX tool can determine whether the comment resulted in the customer saying they would never return to the store or brand, whether the problem was as a result of another customer, or if the opinion resulted from a problem with an online shop.
Social media provides a window into a consumer’s world. Both positive and negative comments are inevitable, and until now even the most sophisticated tools would simply focus on tallying these up.
Now, AI makes it possible to learn the intent behind a message - acting as an early warning system for brands and retailers. This gives retail brands a massive advantage, as it enables trends to be identified early and engage with customers in an even more powerful and meaningful way. Grocery retailers are already fighting it out to grab attention on social media, but by harnessing more intelligent insights, retailers can ensure that customer feedback is relayed accurately and improvements can be made to deliver a stronger customer experience.