One of the technologies we’re using at In The Pocket to help digital products understand their users is sensor mining.

One of the concepts that’s often mentioned when talking about machine learning is the mining of data. Data mining can be defined as the process that starting from both structured and unstructured data tries to extract knowledge and/or unknown interesting patterns by using machine learning algorithms.

Trending & anomaly detection

Anomaly detection is the identification of rare items, events or observations which raise suspicions by differing significantly from the majority of the data. It’s the perfect technique to detect certain problems with your digital platform.


Detection & forecasting

The desire to forecast events and trends is as old as humanity. Whether it’s the weather, the customer demands or the production capacity: we want to be able to know what’s next based on the historic data. Machine learning is the perfect technology to create models that can detect specific trends and extrapolate them to predict how they will evolve.

Churn prediction

When you’re building an online platform - whether it’s an application, a digital tool or webshop - it’s important to attract users. But what’s even more important, is keeping them. Churn prediction is a technique to know which users are going to stop using your platform in the future. By creating a churn prediction model based on the data of your customers, you get an overview of how (often) they use your platform. When you notice some users are starting to lose interest, you can contact them with a special offer. It’s important to detect these customers as early as possible, so you can react proactively.

User segmentation and clustering

No one is exactly the same, but when your user base is growing, specific groups tend to behave the same. Knowing which users show similar behavior is useful to for instance develop new features or send specific marketing mails to different groups. Machine learning helps you create models to segment your user base by implementing data about them and their behavior.

Download the AI Value Canvas

Similar to the business model canvas, we have created an AI Value Canvas Toolkit which helps you crystallize your needs, and avoid technical discussion about neural networks. Use this canvas to identify your AI opportunities today!

Learn More
Learn More