Delays is a big factor when considering taking the public transportation or taking your own car. If delays were more predictable, more people would take the bus instead. This thesis results can be used to further develop more robust systems for predicting delays, thus, more people using the public transportation systems. This was done in collaboration with Hogia. Hogia is a company in Sweden that have their own solutions for calculating delays within public transportation. This thesis investigates if predictions using Machine Learning can improve Hogia’s predictions on bus delays. Python and various libraries are used for training and testing the Machine Learning model. The data available for this study was gathered and provided by Hogia. Raw data were analyzed and preprocessed to create and find features in it, and then used to train a Random Forest Regressor. The model’s predictions are analyzed with various measurements and then compared against their current solution, as well as the actual delays. The result of this study looks promising since only a small dataset of 30 days was used. Also, it gives an understanding of what features that can be of value when training a model. Even though the model’s predictions were in some cases far off compared to Hogia’s current solution due to outliers in the data, this study can be used for further research of utilizing Machine Learning for predicting delays.

Public bus transit operates within an intricate network of routes and stops, where delays are common and can propagate throughout the transit system, affecting systemreliability, passenger satisfaction, and operational efficiency. Existing research on bus delay propagation has primarily focused on route-level delays correlation-basedanalysis, lacking a comprehensive understanding of underlying causal mechanisms of bus delay propagation from a network-level perspective. To enhance our understanding of bus delay propagation within urban transit systems, this study aims to develop a new approach that captures the causal relationshipsbetween stop delays, integrating their temporal and spatial characteristics. Utilizing a causal discovery algorithm for time series data, the thesis infers causal relationshipsfrom bus operation time series data. It then analyze the resulting causal graphs based on complex network measurement indicators. A case study using GTFS data of Stockholm, Sweden, was conducted. The results reveal that stops with a high degree of connections significantly influence delay propagation, with the network exhibiting a community structure that includes both high-degree and low-degree stops. Stops are classified based on their levels into four distinct delay propagation patterns. Critical stops are identified as either delay aggravation or absorption stops, based on their Momentary Conditional Independence (MCI) values. A new metric was constructed, underscoring the importance of considering delays across the entire network rather than isolating analysis to individual routes. The comparison with traditional correlation-based analysis highlights instances of low correlation among stops with high causality and high correlations without underlying causality, emphasizing the deeper insight from the causal approach