Title: Using analysts' forecasts for stock predictions: An entropic tilting approach
Authors: Christoph Frey - University of Konstanz (Germany) [presenting]
Abstract: Predictive density forecasts for US stock returns from Bayesian vector autoregressions are combined with financial analysts' forecasts via entropic tilting. The predictive density of the asset returns is modified to match certain moment conditions that are formed based on average analysts' forecasts, for example, sell and buy recommendations or target prices. The advantage of this approach is that we can combine model-based time-series information with external, forward-looking information in a parsimonious way using closed-form solutions. We show that the tilting approach based on the (possibly biased) professional forecasts leads to an increase in prediction accuracy for both point and density forecasts. This also translates into portfolio gains for an investor who maximizes her expected utility.