Györfi, LászlóLugosi, GáborMorvai, GusztávUniversitat Pompeu Fabra. Departament d'Economia i Empresa2017-07-262017-07-261998-04-01IEEE Transactions on Information Theory, 45, (1999), pp. 2642-2650http://hdl.handle.net/10230/922We present a simple randomized procedure for the prediction of a binary sequence. The algorithm uses ideas from recent developments of the theory of the prediction of individual sequences. We show that if the sequence is a realization of a stationary and ergodic random process then the average number of mistakes converges, almost surely, to that of the optimum, given by the Bayes predictor.application/pdfengL'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commonsinfo:eu-repo/semantics/workingPaperpredictionergodic processespattern classificationStatistics, Econometrics and Quantitative Methodsinfo:eu-repo/semantics/openAccess