در هنگام جستجو کلمه در قسمت عنوان میتوانید کلمات مورد جستجو را با کاراکتر (-) جدا کنید.
کاربرد نوع شرط:
- جایگاه : پژوهشی
- مجله: Journal of computer and Robotics
- نوع مقاله: Journal Article
- کلمات کلیدی: stock price,Neural network,Predict,multi-step-ahead prediction
- چکیده:
- چکیده انگلیسی: Modelling and forecasting Stock market is a challenging task for economists and engineers since it has a dynamic structure and nonlinear characteristic. This nonlinearity affects the efficiency of the price characteristics. Using an Artificial Neural Network (ANN) is a proper way to model this nonlinearity and it has been used successfully in one-step-ahead and multi-step-ahead prediction of different stocks prices. Several factors, such as input variables, preparing data sets, network architectures and training procedures, have huge impact on the accuracy of the neural network prediction. The purpose of this paper is to predict multi-step-ahead prices of the stock market and derive the method, based on Recurrent Neural Networks (RNN), Real-Time Recurrent Learning (RTRL) networks and Nonlinear Autoregressive model process with exogenous input (NARX). This model is trained and tested by Tehran Securities Exchange data.
- انتشار مقاله: 10-09-1393
- نویسندگان: Mohammad Talebi Motlagh,Hamid Khaloozadeh
- مشاهده
- جایگاه : پژوهشی
- مجله: International Journal of Industrial Electronics Control and Optimization
- نوع مقاله: Journal Article
- کلمات کلیدی: Cost function,Optimal Portfolio,Prediction Price,Covariance Matrix Adaptation-Evolution Strategy
- چکیده:
- چکیده انگلیسی: Capital portfolio management is considered an important issue in the field of economics and its main subject is about the scientific management of combination choice of assets that meet the specific investment objectives. Maximizing returns and minimizing asset risk are the most important goals in the management of the portfolio of capital. This paper proposes two novel risk measures based on the MLP neural networks and prediction intervals (PI). The MLP based risk is constant and assumes that the uncertainty is uniform in the dataset. The second one is a time-varying risk measure that doesn’t assume uniformity condition. After introducing two novel risk measures, a new cost function is presented to consider the expected returns and the involving risk at the same time. Finally, the covariance matrix adaptation evolution strategy (CMA-ES) algorithm is used to obtain the optimal portfolio. The validity of the proposed selection process (including risk measures, cost function, and the optimization method) is tested using the dataset of the 18 shares of the Tehran Stock Exchange, and the results are compared with the obtained portfolio using the conditional value at risk (CVaR) criterion as a well-known benchmark.
- انتشار مقاله: 12-04-1397
- نویسندگان: S. Amir Ghoreishi,Hamid Khaloozadeh
- مشاهده
- جایگاه : پژوهشی
- مجله: International Journal of Industrial Electronics Control and Optimization
- نوع مقاله: Journal Article
- کلمات کلیدی: Stock market,neural networks,Forecast Combination,Density Forecasting,Simple Average
- چکیده:
- چکیده انگلیسی: Today, stock market plays a key role in the economy of any country and is considered as one of the growth indicators of any economy. Gaining the skills of gathering and analyzing data simultaneously, as well as using this knowledge in economic investigations, make time and precision factors to be the drawcard of any investor in competition with others. Therefore, having a predictive approach with the lowest degree of error will lead to smarter management of resources. Due to the complex and stochastic nature of the stock market, conventional forecasting approaches in this field have usually faced serious challenges, most notably losing the robustness when the data type changed over time. Moreover, by focusing on point forecasting, some useful statistical information about the objective random variable has been ignored inadvertently, undermining the prediction efficiency. The focus of this study is on density forecasting models which, unlike point forecasting, contain a description of uncertainty. Also, to take advantage of the diversity and robustness features of the combination, instead of an individual prediction, a combination of the density forecasting given by the different structures of ARMA, ANN, and RBF models is presented. In order to analyze the capabilities of these approaches in Tehran Stock Exchange (TSE), two basic methods of this category have been used to predict the price of MAPNA stock -one of the fifty active companies in this market- in the period 2012 to 2019.
- انتشار مقاله: 10-10-1398
- نویسندگان: S.Raheleh Shahrokhi,Hamid Khaloozadeh,HamidReza Momeni
- مشاهده
- جایگاه : پژوهشی
- مجله: Advances in Mathematical Finance and Application
- نوع مقاله: Journal Article
- کلمات کلیدی: Tail Mean-Variance criterion,Optimal portfolio selection,Efficient Frontier,Skew-Elliptical Distributions
- چکیده:
- چکیده انگلیسی: In portfolio theory, it is well-known that the distributions of stock returns often have non-Gaussian characteristics. Therefore, we need non-symmetric distributions for modeling and accurate analysis of actuarial data. For this purpose and optimal portfolio selection, we use the Tail Mean-Variance (TMV) model, which focuses on the rare risks but high losses and usually happens in the tail of return distribution. The proposed TMV model is based on two risk measures the Tail Condition Expectation (TCE) and Tail Variance (TV) under Generalized Skew-Elliptical (GSE) distribution. We first apply a convex optimization approach and obtain an explicit and easy solution for the TMV optimization problem, and then derive the TMV efficient frontier. Finally, we provide a practical example of implementing a TMV optimal portfolio selection in the Tehran Stock Exchange and show TCE-TV efficient frontier.
- انتشار مقاله: 09-11-1398
- نویسندگان: Esmat Jamshidi Eini,Hamid Khaloozadeh
- مشاهده