In this thesis a model capable of predicting taxidemand with high accuracy across five different real world single company datasets is presented. The model uses historical drop off and arrival information to make accurate shortterm predictions about future taxi demand. The model is compared to and outperforms both LSTM and statistical baselines. This thesis uniquely uses a different tessellation strategy which makes the results directly applicable to smaller taxi companies. This paper shows that accurate short term predictions of taxi demand can be made using real world data available to taxi companies. MSE is also shown to be a more robust to uneven demand distributions across cities than MAE. Adding drop offs to the input had provided only marginal improvements in the performance of the model.

Supplying the right amount of taxis in the right place at the right time is very important for taxi companies. In this paper, the machine learning model Taxi Demand Net (TDNet) is presented which predicts short-term taxi demand in different zones of a city. It is based on WaveNet which is a causal dilated convolutional neural net for time-series generation. TDNet uses historical demand from the last years and transforms features such as time of day, day of week and day of month into 26-hour taxi demand forecasts for all zones in a city. It has been applied to one city in northern Europe and one in South America. In northern europe, an error of one taxi or less per hour per zone was achieved in 64% of the cases, in South America the number was 40%. In both cities, it beat the SARIMA and stacked ensemble benchmarks. This performance has been achieved by tuning the hyperparameters with a Bayesian optimization algorithm. Additionally, weather and holiday features were added as input features in the northern European city and they did not improve the accuracy of TDNet.