Short-Term Forecasting of Taxi Demand using a two Channelled Convolutional LSTM network
Abstract: 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.
AT THIS PAGE YOU CAN DOWNLOAD THE WHOLE ESSAY. (follow the link to the next page)