Many proposed extensions to the Standard Model of particle physics predict long-lived particles, which can decay at a significant distance from the primary interaction point. Such events produce displaced vertices with distinct detector signatures when compared to standard model processes. The Large Hadron Collider (LHC) operates at a collision rate where it is not feasible to record all generated data—a problem that will be exac-erbated in the coming high-luminosity upgrade—necessitating an online trigger system to decide which events to keep based on partial information. However, the trigger is not directly sensitive to signatures with displaced vertices from Long-lived particles (LLPs). Current LLP detection approaches require a computationally expensive reconstruction step, or rely on auxiliary signatures such as energetic particles or missing energy. An improved trigger sensitivity increases the reach of searches for extensions to the standard model.This thesis explores the possibility to apply machine learning methods directly on low-level tracking features, such as detector hits and hit-pairs to identify displaced high-mass decays while avoiding a full vertex and track reconstruction step.A dataset is developed where modelled displaced signatures from novel and known physics processes are mixed in a custom simulation environment, which models the in-ner detector of a general purpose particle detector. Two machine learning models are evaluated using the dataset: a multi-layer dense Artificial Neural Network (ANN), and a Graph Neural Network (GNN). Two case studies suggest that dense ANNs have difficulty capturing relational information in low-level data, while GNNs can feasibily discriminate heavy displaced decay signatures from a Standard Model background. Furthermore it was found that GNNs can perform at a background rejection factor of 103 and a signal efficiency of 20% in collision environments with moderate levels of pile-up interactions, i.e. low-energy particle collisions simultaneous with the primary hard scatter. Further work is required to integrate the approach into a trigger environment. In particular, detector material and measurement resolution effects should be included in the simulation, which should be scaled to model the High-Luminosity Large Hadron Collider (HL-LHC) with its more complicated geometry and its high levels of pile-up.In parallel, the machine learning landscape is quickly evolving and concentrating into large software frameworks with expanding scope, while the High-Energy Physics (HEP) community maintains its own set of tools and frameworks, one example being the Toolkit for Multivariate Analysis (TMVA) which is part of the ROOT framework. This thesis discusses the long- and short-term evolution of these tools, both current trends and some relations to parallel developments in Industry 4.0.