Abstract

https://ssrn.com/abstract=2894287
 


 



Recursive Portfolio Selection with Decision Trees


Anton Andriyashin


Humboldt University of Berlin - Center for Applied Statistics and Economics

Wolfgang K. Härdle


Humboldt University of Berlin - Institute for Statistics and Econometrics; Humboldt University of Berlin - Center for Applied Statistics and Economics (CASE)

Roman Vladimirovich Timofeev


Humboldt University of Berlin - Institute for Statistics and Econometrics

January 15, 2008

SFB 649 Discussion Paper 2008-009

Abstract:     
A great proportion of stock dynamics can be explained using publicly available information. The relationship between dynamics and public information may be of nonlinear character. In this paper we offer an approach to stock picking by employing so-called decision trees and applying them to XETRA DAX stocks. Using a set of fundamental and technical variables, stocks are classified into three groups according to the proposed position: long, short or neutral. More precisely, by assessing the current state of a company, which is represented by fundamental variables and current market situation, well reflected by technical variables, it is possible to suggest if the current market value of a company is underestimated, overestimated or the stock is fairly priced. The performance of the model over the observed period suggests that XETRA DAX stock returns can adequately be predicted by publicly available economic data. Another conclusion of this study is that the implied volatility variable, when included into the training sample, boosts the predictive power of the model significantly.

Number of Pages in PDF File: 27

Keywords: CART, decision trees in finance, nonlinear decision rules, asset management, portfolio optimisation

JEL Classification: C14, C49, G11, G12


Open PDF in Browser Download This Paper

Date posted: January 9, 2017  

Suggested Citation

Andriyashin, Anton and Härdle, Wolfgang K. and Timofeev, Roman Vladimirovich, Recursive Portfolio Selection with Decision Trees (January 15, 2008). SFB 649 Discussion Paper 2008-009. Available at SSRN: https://ssrn.com/abstract=2894287

Contact Information

Anton Andriyashin
Humboldt University of Berlin - Center for Applied Statistics and Economics ( email )
Spandauer Strasse 1
Berlin, D-10178
Germany
Wolfgang K. Härdle (Contact Author)
Humboldt University of Berlin - Center for Applied Statistics and Economics (CASE)
Unter den Linden 6
Berlin, D-10099
Germany
Humboldt University of Berlin - Institute for Statistics and Econometrics ( email )
Unter den Linden 6
Berlin, D-10099
Germany
+49 30 2093 5631 (Phone)
+49 30 2093 5649 (Fax)
Roman Vladimirovich Timofeev
Humboldt University of Berlin - Institute for Statistics and Econometrics ( email )
Spandauer Str. 1
Berlin, D-10178
Germany
Feedback to SSRN


Paper statistics
Abstract Views: 203
Downloads: 56
Download Rank: 293,569