Optimizing Financial Portfolios from the Perspective of Mining Temporal Structures of Stock Returns
نویسندگان
چکیده
In this paper, we aim at introducing how one of the recently developed statistical learning techniques, temporal factor analysis (TFA), which is originally devoted for further study of the arbitrage pricing theory (APT), could be exploited in financial data mining to determine weights in portfolio optimization problem. Furthermore, we study several variants of the APT-based Sharpe ratio maximization technique that utilize the concepts of portfolio downside risk and upside volatility tailored-made for the need of risk-averse as well as aggressive profit-seeking investors.
منابع مشابه
Optimizing Stock Portfolio of Investment Companies Operating in Field of Petrochemical and Refinery Based on Multivariate GARCH Models
The main objective of this research is to optimize the stock portfolio of investment companies operating in the field of petrochemical and refining industries through minimizing risk with respect to the expected return. In this regard, first of all, the compositions of sample firm's portfolios were investigated during 2013 to 2016 and high-weight industries were selected. Then, the risk of retu...
متن کاملOverreaction & Under reaction: Evaluating performance and Speed of Adjustment Investment Strategies in Tehran Stock Exchange (TSE)
In this research, overreaction and underreaction have been studied by assessing profitability and excess returns of investment strategies and evaluating price adjustment speed in short and long terms. The results showed that the momentum investment strategies had higher annual returns in comparison to contrarian strategies in all short and long periods which led to confirmation of underreaction...
متن کاملExamination of the Predictive Power of Fama-French Five-Factor Model by the Inclusion of Skewness Coefficient: Evidence of Iranian Stock Market
Due to the complexity of financial markets and specialization of investment, the investors in financial markets need tools, methods and models by which they can choose the best investment and the most appropriate portfolios. Fama-French Five-Factor Model (FFFFM) is one of the newest methods among various methods for financial asset pricing and prediction of stock returns. The main aim of this r...
متن کاملPortfolio ranking: using finance technology set in DEA models (Case Study: Tehran Stock Exchange)
One of the most important concerns of investors in financial markets is choosing a share or stock portfolio that is optimal in terms of profitability. To this end, there are many ways in which the stock portfolio has been chosen. The optimal portfolio selection is a portfolio management goal. In this dissertation, the DEA technique has been used as a new and reliable way to select the stock opt...
متن کاملStock Selection Based on a Hybrid Quantitative Method
Quantitative stock selection has become a research hotspot in the field of investment decision. As the data mining technology becomes mature, quantitative stock selection has made great progress. From the perspective of value investment, this paper selects top 200 stocks of A share in terms of market value. With the random forest (RF), financial characteristic variables with significant impact ...
متن کامل