Forecasting

The main objective of this study is to find out whether an Artificial Neural Network (ANN) will be useful to predict stock market price، which is highly non-linear and uncertain. Specifically، this study will focus on forecasting TSE Price Index (TEPIX) as the most significant index of Iran Stock Market. Many data have been used as inputs to the network. These data are observations of 2000 days for a period of 9 years from 02/29/2000 to 12/03/2008. Data are divided into two categories; fundamental and technical data. The fundamental data used here are principal economic values like Dollar/Rials Exchange Rate، Gold price and Oil price. The technical data used are technical indices such as Moving Average (MA)، Moving Average Convergence/Divergence (MACD)، Relative Strength Index (RSI)، Rate of Change (ROC)، Momentum (MOM) and daily trading volume of stocks. The selected data are divided into training set and test set، in order to be entered into the network and the remaining 10% was used as the testing set. Training set consists 90% of data. This classification uses 3 different approaches to assemble the training and test data، including random، deterministic and consecutive selection. Here، a feed-forward neural network (FFNN) with the most suitable algorithm for finance (i.e. Back Propagation algorithm) was used for the prediction. Predictions were made for the next day of TEPIX with a 3-4-1 topology and 1500 epochs. The performance of the ANN was evaluated by MSE. Finally، the results showed that ANN could properly recognize the relationships between fundamental and technical data and TEPIX، so that the prediction of the next day was quite possible.

This paper focuses on the development of modern non-structural dynamic multivariate time series models and evaluating performance of various alternative specifications of these models for forecasting Iranian inflation. The Quasi-Bayesian method, with Literman prior, is applied to Vector autoregressive (VAR) model of the Iranian economy from 1981:Q2 to 2006:Q1 to assess the forecasting performance of different models over different forecasting horizons. The Bewley transformation is also employed for the re-parameterization of the VAR models to impose the mean of the change of inflation to zero. Applying the Bewley (1979) transformation to force the drift parameter of change of inflation to zero in the VAR model improves forecast accuracy in comparison to the traditional BVAR.

During the recent decades, neural network models have been focused upon by researchers due to their more real performance and on this basis, different types of these models have been used in forecasting. Now, there is a question that which kind of these models has more explanatory power in forecasting the future processes of the stock. In line with this, the present paper made a comparison between static and dynamic neural network models in forecasting (uninvariable) the return of Tehran Stock Exchange (TSE) index in order to find the best model to be used for forecasting this series. The data were collected daily from 26/11/2009 to 17/10/2014. The models examined in this study included two static models (Adaptive Neuro-Fuzzy Inference Systems ""ANFIS"" and Multi-layer Feed-forward Neural Network ""MFNN"") and a dynamic model (nonlinear neural network autoregressive model ""NNAR""). The findings showed that based on the Mean Square Error and Root Mean Square Error criteria, ANFIS model had a much higher forecasting ability compared to other models.

هدف از تدوین این مقاله، پیش بینی عرضه و تقاضای نیروی کار در ایران و سپس شکاف میان این دو تا سال 1430بوده و برای پیش بینی عرضه، نخست جمعیت به تفکیک سن با روش کوهورت تا سال 1430 برآورد شده، سپس با دو سناریو برای نرخ مشارکت نیروی کار جمعیت فعال یا عرضه نیروی کار پیش بینی شده است. سناریوی واقع بینانه که نرخ مشارکت نیروی کار را متناسب با روند «متوسط سال های تحصیل زنان» پیش بینی می کند، جمعیت فعال در سال 1430 را 35/30 میلیون نفر پیش بینی کرده، و از طرف دیگر، با استفاده از کشش تولیدی اشتغال و دو سناریو برای رشد اقتصادی ایران، تقاضا برای نیروی کار تا سال 1430 پیش بینی شده است. با فرض رشد اقتصادی متوسط 6/2 درصد در سال و کشش تولیدی 7/0، میزان تقاضا برای نیروی کار در سال 1430، حدود 26/40 میلیون نفر پیش بینی شده است. با سناریوی واقع بینانه برای نرخ مشارکت و سناریوی رشد اقتصادی سالانه 6/2 درصد، نتایج نشان می دهد که تا سال 1410، بیکاری در ایران وجود دارد هرچند که روند آن کاهشی است. در سال 1410، بیکاری به صفر می رسد؛ یعنی عرضه و تقاضا باهم برابر می شوند. از سال 1410 به بعد، مازاد تقاضای نیروی کار با روند افزایشی شروع خواهد شد؛ به طوری که در سال 1430، مازاد تقاضا برای نیروی کار به حدود 10 میلیون نفر می رسد. برای جذب مازاد تقاضای نیروی کار، سه پیشنهاد سیاستی ارائه شده است: اول، افزایش بهره وری؛ دوم، استفاده از نیروی کار خارجی و سوم، افزایش نرخ مشارکت اقتصادی زنان.