A benchmark framework for trajectory vectorization in unsupervised settings

The growth of location-tracking technologies has generated large spatiotemporal datasets that require efficient analysis methods. Recent approaches focus on vectorizing the data as a preprocessing step to enable the application of off-the-shelf classical machine learning techniques. To date, such approaches have primarily been evaluated in supervised tasks. This paper presents a benchmark framework for assessing these methods in unsupervised settings, where no target labels are available. We extend and systematically evaluate four families of vectorization techniques: feature-based, shapelet-based, dictionary-based, and matrix-based. The framework assesses both clustering quality and cross-vectorization diversity through quantitative and qualitative analyses. Overall, the findings demonstrate that these vectorization approaches offer a valuable option for unsupervised trajectory analysis. Additionally, our paper provides insight into which vectorization technique is most suitable for the specific characteristics of the task under analysis.