When your model learns more than it should There is a quiet assumption in most machine learning projects. If the model is accurate, then it must be good. That assumption works well, until the model starts making decisions about people, money, risk, or opportunity. Then accuracy alone is not enough. A model can be very accurate and still systematically treat groups differently. This is the ninth article in our series " The Theory behind Qlik Predict ". So far, we have talked

Have you ever opened a dashboard and felt lost, unsure of where to look first? Or needed a quick piece of information, only to find it buried among too many charts and filters that did not work well together? That is exactly what UX, or User Experience, is about. When we talk about dashboards, UX is not just about making them look more attractive. It is about efficiency, clarity, and supporting better decision-making. UX means ensuring that the people using a dashboard can fi

Machine Learning has become more accessible than ever. With tools like Qlik Predict and other AutoML platforms, building a model no longer requires writing code or tuning algorithms manually. But accessibility does not mean simplicity. In this video, Igor Alcantara walks through the Top 10 Mistakes in a Machine Learning project, especially in AutoML environments. These are the errors that quietly destroy performance long before an algorithm fails. From vague business questio