Effective transport planning strategies seek to improve urban transportation systems by addressing traffic congestion problems, identifying emission hotspots, incentivising  public transit and adoption of electric vehicles. Strategy makers are increasingly relying on new emerging methods such as full population scaled agent-based simulation models to study the interaction between mobility patterns of the commuters and their impact on the transportation systems. This is because the behavioural changes in daily travelling patterns of commuters play a major role in predicting the future travel demand for the development of a robust and reliable urban transportation system. It is not possible for the traditional surveys to sample a large majority of daily commuter trips that serve as input to full sample agent-based simulation. In this paper, we use the household travel survey data of Singapore to generate synthetic mobility patterns for the complete population of private vehicle users by using a multi-headed gated recurrent unit (GRU) based generative model. We define and utilize two accuracy evaluation metrics that quantify the quality of the generated synthetic mobility trips. Our experimental results have shown that we are able to capture 90\% of the correctness of the original mobility dataset of private vehicle users.