The Classification of Stocks with Basic Financial Indicators: An Application of Cluster Analysis on the BIST 100 Index

Abstract

In the literature, it is seen that has been used the data mining methods frequently for the analysis of the stock market and stocks. The aim in here is to provide making the most rational choice and increasing return by reducing human intervention to a minimum level with the creating the algorithmic process structure. In this study, stocks are classified basis of financial indicators derived from the financial statements of the companies. For this purpose, cluster analysis which is one of the data mining and multivariate statistical methods is used. In this method the aim is to collect most similar the stocks in the same cluster in terms of related variables. The variables used in the study; Price/earnings ratio, market value/book value ratio, dividend yield, return on assets, return on equity, change in sales and equity, return on average, return and risk. As the result of the analysis, 88 stocks in Borsa Istanbul 100 Index are divided into 12 clusters. Among these stocks, the ones that are most suitable to form a portfolio have been tried to be determined based on financial indicators and last one and three years’ stock performances.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 12 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.