The seismic building structural type (SBST) reflects the main load-bearing structure of a building and therefore its behaviour under seismic load. For numerous areas in earthquake prone regions this information is outdated, unavailable, or simply not existent. Traditional methods to gather this information, such as building-by-building inspections, are costly and highly time-consuming, making them unfeasible for assessing large building inventory. For this reason, the use of remote sensing data has been proposed to allow a fast acquisition of relevant building information on urban and regional scale. Subsequently, machine learning algorithms may be used to analyse the gathered data, e.g. to classify a building stock into groups with similar seismic behaviour. This thesis investigates into such an approach for the building stock of Groningen in the Netherlands. Our focus lies on the extraction of detailed geometric information from a point cloud gained by aerial laser scanning. We thereby follow the assumption that similar structural systems and materials can be inferred from geometric similarities. To describe the geometric shape of a building we apply Shape DNA, a spectral shape descriptor based on the eigenvalues of the Laplace-Beltrami operator. In a first experiment on a synthetically generated building stock we succeed in predicting the roof type of different buildings with accuracies above 80%, only relying on the Shape DNA. The experiment shows promising results, however, further research is necessary in order to explore the usability on real building data. In a second experiment we use a sample of buildings from the Groningen building stock. Here we can automatically predict detailed SBST information, such as the type of lateral load resisting system, with accuracies above 80% only by taking a buildings footprint area and year of construction into account. (see thesis document for extended abstract)