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.