Each individual in society experiences an evolution of their income during their lifetime. Macroscopically, this dynamic creates a statistical relationship between age and income for each society. In this study, we investigate income distribution and its relationship with age and identify a stable joint distribution function for age and income within the United Kingdom and the United States. We demonstrate a flexible calibration methodology using panel and population surveys and capture the characteristic differences between the UK and the US populations. The model here presented can be utilised for forecasting income and planning pensions.

Saving and investment behaviour is crucial for all individuals to guarantee their welfare during work-life and retirement. We introduce a deep reinforcement learning model in which agents learn optimal portfolio allocation and saving strategies suitable for their heterogeneous profiles. The environment is calibrated with occupation- and age-dependent income dynamics. The research focuses on heterogeneous income trajectories dependent on agents’ profiles and incorporates the parameterisation of agents’ behaviours. The model provides a new flexible methodology to estimate lifetime consumption and investment choices for individuals with heterogeneous profiles.