Human trajectory anomaly detection is critical for applications such as security surveillance and public health, yet most existing methods focus on vehicle-level traffic, with limited attention to human-level trajectories. Due to the inherent sparsity of human trajectory data, machine learning approaches are favored for detecting complex patterns. However, concerns about model biases and robustness have highlighted the need for more transparent and explainable solutions. In this paper, we propose a lightweight anomaly detection model specifically designed to detect anomalies in human trajectories. We propose a Neural Collaborative Filtering approach to model and predict normal mobility. Our method is designed to model users’ daily patterns of life without requiring prior knowledge, thereby enhancing performance in scenarios where data is sparse or incomplete, such as in cold start situations. Our algorithm consists of two main modules. The first is the collaborative filtering module, which applies collaborative filtering to model normal mobility of individual humans to places of interest. The second is the neural module, responsible for interpreting the complex spatio-temporal relationships inherent in human trajectory data. To validate our approach, we conducted extensive experiments using simulated and real-world datasets comparing to numerous state-of-the-art trajectory anomaly detection approaches.