FILTRATION OF FINANCIAL TIME SERIES USING NON29 NEGATIVE MATRIX FACTORIZATION METHODS Cover Image

FILTRACJA FINANSOWYCH SZEREGÓW CZASOWYCH 2 METODAMI NIEUJEMNEJ FAKTORYZACJI MACIERZY
FILTRATION OF FINANCIAL TIME SERIES USING NON29 NEGATIVE MATRIX FACTORIZATION METHODS

Author(s): Paweł Rubach, Ryszard Szupiluk
Subject(s): Economy, Methodology and research technology
Published by: Szkoła Główna Gospodarstwa Wiejskiego w Warszawie
Keywords: time-series filtration; trend estimation; non-negative matrix 38 factorization;

Summary/Abstract: In this paper, we will present a method of multivariate filtration 31 that may be used to eliminate noise and estimate trends in financial time32 series. A significant element of the filtration process is the decomposition of 33 time-series using nonnegative matrix factorization. The presented method 34 may be applied in many practical aspects of finance and management, in 35 particular for use in technical analysis of financial markets, trading systems 36 or risk models.

  • Issue Year: XIX/2018
  • Issue No: 3
  • Page Range: 284-292
  • Page Count: 9
  • Language: Polish