We describe a strategy applicable to the investment part of the M6 Forecasting Competition, which maximizes the probability of securing at least the top q-th rank. This portfolio strategy can attain a comparable probability of winning as a participant capable of consistently generating...

This short note outlines the general approach used for the forecasting part of the M6 forecasting competition. It describes a meta-learning approach that is based on an encoder-decoder hypernetwork, capable of identifying the most appropriate parametric model for a given family of related...