<abstract xmlns="http://www.w3.org/1999/xhtml"><p> The paper develops the concept of harnessing data classification methods to recognize patterns in stock prices. The author defines a formation as a pattern vector describing the financial instrument. Elements of such a vector can be related to the stock price as well as sales volume and other characteristics of the financial instrument. The study uses data concerning selected companies listed on the stock exchange in New York. It takes into account a number of variables that describe the behavior of prices and volume, both in the short and long term. Partitioning around medoids method has been used for data classification (for pattern recognition). An evaluation of the possibility of using certain formations for practical purposes has also been presented.</p></abstract>

The paper develops the concept of harnessing data classification methods to recognize patterns in stock prices. The author defines a formation as a pattern vector describing the financial instrument. Elements of such a vector can be related to the stock price as well as sales volume and other characteristics of the financial instrument. The study uses data concerning selected companies listed on the stock exchange in New York. It takes into account a number of variables that describe the behavior of prices and volume, both in the short and long term. Partitioning around medoids method has been used for data classification (for pattern recognition). An evaluation of the possibility of using certain formations for practical purposes has also been presented.

Forecasting Changes in Stock Prices on the Basis of Patterns Identified with the Use of Data Classification Methods

Ph.D. Wroclaw University of Economics Department of Economic Forecasts and Analyses Komandorska 118/120, Wrocław, Poland

Folia Oeconomica Stetinensia

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

The paper develops the concept of harnessing data classification methods to recognize patterns in stock prices. The author defines a formation as a pattern...

Forecasting Changes in Stock Prices on the Basis of Patterns Identified with the Use of Data Classification Methods

Online veröffentlicht: 11. Dez. 2014

Seitenbereich: 7 - 21

Eingereicht: 18. Nov. 2013

Akzeptiert: 01. Juli 2014

DOI: https://doi.org/10.2478/foli-2014-0101

Schlüsselwörter
data classification, cluster analysis, partitioning around medoids, technical analysis, price patterns

© University of Szczecin

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Forecasting Changes in Stock Prices on the Basis of Patterns Identified with the Use of Data Classification Methods

Online veröffentlicht: 11. Dez. 2014

Seitenbereich: 7 - 21

Eingereicht: 18. Nov. 2013

Akzeptiert: 01. Juli 2014

DOI: https://doi.org/10.2478/foli-2014-0101

Schlüsselwörterdata classification, cluster analysis, partitioning around medoids, technical analysis, price patterns

© University of Szczecin

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Schlüsselwörter
data classification, cluster analysis, partitioning around medoids, technical analysis, price patterns