UNSUPERVISED CLASSIFICATION OF JAPANESE CANDLESTICKS: TECHNICAL ANALYSIS VS MACHINE LEARNING
UNSUPERVISED CLASSIFICATION OF JAPANESE CANDLESTICKS: TECHNICAL ANALYSIS VS MACHINE LEARNING
Author(s): Maciej Janowicz, Luiza OchnioSubject(s): Micro-Economics, Financial Markets, ICT Information and Communications Technologies
Published by: Szkoła Główna Gospodarstwa Wiejskiego w Warszawie
Keywords: Japanese candlesticks; foreign exchange market; unsupervised learning;
Summary/Abstract: The unsupervised clusterization of a set of Japanese Candlesticks generated by the currency pair prices on the Forex market has been performed. Several algorithms that do not require the number of clusters in advance have been used. It turns out that different algorithms give glaringly different numbers and description of clusters. Comparison with well-established candlestick types known from the technical analysis has been made.
Journal: Metody Ilościowe w Badaniach Ekonomicznych
- Issue Year: XXVI/2025
- Issue No: 4
- Page Range: 141-154
- Page Count: 14
- Language: English
