Intergamma is a franchise organization for construction markets in The Netherlands and Belgium. The organization is market leader in the Do It Yourself market in the Benelux and exploits two different store formulas; GAMMA and KARWEI.
Gamma, the biggest construction store in The Netherlands, has existed for 45 years now and has 245 stores located in Belgium and The Netherlands.
Karwei, the construction store with more of a focus on decoration, has 136 stores through The Netherlands and has existed for almost 40 years now.
Intergamma is responsible for compiling the assortment for their franchisees, as well as the sales guidance and publicity. They also offer further educations and deliver services in the area of automation and logistics for the Gamma and Karwei stores.
Intergamma stores and analyzes their data, just like most businesses nowadays. In the past, they did this on-premise, which made their data hard to access, analyze and use. They wanted to be more data-driven and manage and store their data in a more efficient way; at one place and accessible in real time; the Cloud.
Another challenge they were facing was making sense of all their data, as most of it was unstructured. They were looking for an artificial intelligence solution, to have better insights and to help customers find exactly what they were searching for when doing on-site search queries, even giving them personalized suggestions based on their past search and purchasing behavior.
Intergamma approached Crystalloids Innovations to help them find solutions to these challenges.
Intergamma wanted to have a cloud-based data lake and a machine learning solution for their unstructured data.
Crystalloids Innovations started the process by migrating all the data, stored on different platforms, into one secured data lake; the Google Cloud Platform. Here the data is stored in Google Cloud Storage and Google BigQuery and easily accessible with business intelligence tools like InsightOS and Tableau, but also for the more advanced data analysts and scientists in Cloud Datalab and Google BigQuery.
The data is mainly customer focused, which means that all the different information about one customer is brought together at one place and linked to one customer ID. The products they buy, the frequency of buying, the newsletters they receive etc. All the information is stored and linked. Also, the web behavior of a unique client is being tracked and, based on this information, it’s possible to make personal recommendations, both on-site as through other channels like the newsletter.
The next step was introducing machine learning to make sense of the unstructured data Intergamma was storing. For this, Crystalloids Innovations used TensorFlow; the open-source software library for machine intelligence, developed by Google to meet the need for systems capable of building and training neural networks.
We used the Google Analytics data of Intergamma, which provided all the information on on-site keyword search, the subsequent user clicks on the search results (product views), products cartings, product checkout and product purchases to train our neural network. In the end, machine learning made it possible to optimize the keyword search result list order, called on-site search specific boosting.