17 Pages Posted: 19 Jun 2013 Last revised: 4 Apr 2015
Date Written: February 23, 2015
The Black Litterman (BL) model for portfolio optimization combines investors' expectations with the Markowitz framework. The BL model is designed for investors with private information or with knowledge of market behavior. In this paper I propose a method where investors' expectations are based on accounting variables, recommendations of financial analysts, and social network indicators of financial analysts and corporate directors. The results show promise when compared to those of an investor that only uses market price information. I also provide recommendations about trading strategies using the results of my model.
Keywords: Link mining, social network, machine learning, computational finance, portfolio optimization, boosting, Black Litterman model
JEL Classification: C44, C58, C63, G11
Suggested Citation: Suggested Citation
Creamer, Germán G., Using Link Mining for Investment Decisions: Extending the Black Litterman Model (February 23, 2015). Howe School Research Paper No. 2015-50. Available at SSRN: https://ssrn.com/abstract=2281483 or http://dx.doi.org/10.2139/ssrn.2281483