Chain-structured neural architecture search for financial time series forecasting

arXiv:2403.14695v1 Announce Type: cross
Abstract: We compare three popular neural architecture search strategies on chain-structured search spaces: Bayesian optimization, the hyperband method, and reinforcement learning in the context of financial time series forecasting.

abstract architecture arxiv bayesian context cs.lg financial forecasting neural architecture search optimization popular q-fin.st reinforcement reinforcement learning search series spaces strategies time series time series forecasting type