Nouvez is a Dutch furniture retailer with a product range of almost 2.000 products within the categories furniture, lighting and living accessories. Due to a lack of proper product data delivered from suppliers, the brand wanted to improve the overall data quantity. This could namely lead to an enriched customer experience which could in turn increase the conversion rate. At this point, Squadra Machine Learning Company offered to help the organization with their problem.
Squadra uses Machine Learning to offer smart software solutions to (B2B-) customers. Machine Learning is computer science that gives computers the ability to learn without being explicitly programmed. Instead of writing lines of code with a lot of rules like “if something then do this”, Machine Learning software identifies patterns and creates algorithms based on large sets of data. It is an extremely powerful technique which is able to perform intelligent tasks which were up to now usually done by humans. It can recognize, predict, advice, optimize and classify, and therefore it can support the automation of various business and industrial processes, customer facing services and other data driven functions.
The brand wanted to receive more product data since they found the amount of existing product data insufficient. Suppliers didn’t always deliver proper data, but they still needed as much information as possible in order to sufficiently inform their customers. Nouvez already had pictures of all of their products, and they were wondering whether or not product characteristics could be withdrawn from these images. Squadra assisted in this.
In order to extract data from images, Squadra Machine Learning Company used one of the solutions from Powerenrich.ai: image extraction. In order to test whether or not this solution would work for Nouvez, a proof-of-concept was carried out. It appeared that the algorithm was able to extract some of the product features based on the image. Whether or not a chair had an armrest, the amount of chair legs and the product’s color were all features that were able to be extracted from the image. This information is just the starting point for more possibilities: by using the image-extracted data, you are also able to predict to which product (sub-) category a product belongs. To reach this, a model trained by Nouvez themselves was used. In order to optimize this model, it would also be possible to use a data model that already contains information about furniture.
After collaborating with Squadra Machine Learning Company, Nouvez is now able to provide its customers with more product information. Features were extracted from product images; these features inform your customers which contributes to an enriched customer journey. Product information and product features do not only improve the customer journey, but they also provide possibilities for automating other business processes. As mentioned, they can assist in categorizing products via the Powerclass.ai-tool. Based on these features, it’s also possible to generate unique and qualitative product descriptions with Powertext.ai. Artificial Intelligence is constantly developing which means that more and more business processes can be automated as time passes. It may be profitable to be one of the early adopters of this technological development.