A learning-augmented approach to pricing risk in South Africa

Through application of state-space modelling, the asset pricing model is re-explored. The result is an asset pricing model which tracks the evolution of investor probability beliefs and learning through a Kalman filter. This behaviourally inspired model shows marked improvement over a traditional asset pricing model, with pricing errors being reduced by as much as 41 % over a 16 year period using South African equities data. We find that investors tend to price long-run risk whilst being notably influenced by exposure to lagged market performance. Together, these findings lend support to the hypothesis that investors tend to price risk as a dynamic learning process in an emerging market.