Financial planning via deep reinforcement learning holds much promise. One implementation, AIPlanner, delivered near optimal financial results, but had a major shortcoming. It required training a separate neural network model for each financial scenario. This paper describes extending AIPlanner...

Treating the premium of stocks over bills as a statistical phenomenon, and based on almost a century of historical data, I estimate asset allocation confidence intervals for the optimal retirement investment problem in the presence of guaranteed income. The confidence intervals arise as a result...

I investigate optimal stock/bond asset allocation, gradual SPIA purchase decisions, and consumption decisions in retirement. I use a utility function that is intended to be representative of a retired individual's need for an income floor and desire for upside potential. The optimal strategy is...

A model of labor income that includes volatility is developed based on longitudinal data. Numerical stochastic dynamic programming is then applied to the model to explore the effects of stochastic human capital and Social Security on optimal asset allocation and consumption decisions over the...

This paper introduces AIPlanner, a financial planner based upon deep reinforcement learning. AIPlanner provides an investment and consumption strategy intended to optimize lifetime well-being. The results of AIPlanner are very close to the precise analytical solution, as well as to the precise...

I investigate optimal asset allocation, gradual SPIA purchase decisions, and consumption decisions in retirement using various combinations of stocks, nominal bonds, real bonds, nominal SPIAs, and real SPIAs. I use a utility function that is intended to be representative of a retired...