Predicting the Stock Market

摘要: This paper presents a tuturial introduction to predictions of stock time series. The various approaches technical and fundamental analysis is presented the prediction problem formulated as special case inductive learning. problems with performance evaluation near-random-walk processes are illustrated examples together guidelines for avoiding risk data-snooping. connections concepts like "the bias/variance dilemma", overtraining model complexity further covered. Existing benchmarks testing metrics surveyed some new measures introduced.