مطالب مرتبط با کلیدواژه

Artificial Neural Network (ANN)


۱.

Short-term Prediction of Tehran Stock Exchange Price Index (TEPIX): Using Artificial Neural Network(مقاله علمی وزارت علوم)

نویسنده:
منبع: بورس اوراق بهادار تابستان ۱۳۹۰ شماره ۱۴

کلیدواژه‌ها: Short term Prediction Forecasting Tehran Price Index (TEPIX) Artificial Neural Network (ANN)

حوزه‌های تخصصی:
تعداد بازدید : ۱۵۴۷ تعداد دانلود : ۷۳۲
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.
۲.

Forecasting the Profitability in the Firms Listed in Tehran Stock Exchange Using Data Envelopment Analysis and Artificial Neural Network(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۱, Issue ۲, Autumn ۲۰۱۶ 95 - 104

کلیدواژه‌ها: Artificial Neural Network (ANN) Fuzzy DEA Earnin predicting Decision Making

حوزه‌های تخصصی:
تعداد بازدید : ۸۵۴ تعداد دانلود : ۵۸۸
Profitability as the most important factor in decision-making, has always been considered by stake­holders in the company's profitability. Also can be a basis for evaluating the performance of the managers. The ability to predict the profitability can be very useful to help decision-makers. That's why one of the most important issues is the expected profitability. The importance of these forecasts depends on the amount of misalignment with reality. The amount of deviation is less than the forecast of higher accuracy. Although there are various methods for predicting but the use of artificial intelligence techniques is increasing due to fewer restriction. The aim of this study is to evaluate the predictive power of profitability using DEA and neutral network, to enhance the decision-making users of 2012 to 2015of 7 premier financial ratios were used as independent variables. Test results show that both of ANN and DEA have ability to forecast profitability and given that neutral network prediction accuracy is higher than the DEA, the model predict better the profitability of companies.
۳.

The Effectiveness of Combining Empirical Decomposition Mode and Machine Learning Tools on Bitcoin Volatility Prediction(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۱۰, Issue ۴, Autumn ۲۰۲۵ 485 - 504

کلیدواژه‌ها: Bitcoin Empirical Decomposition Mode (EMD) Artificial Neural Network (ANN) Recurrent Neural Network (RNN) Long Short-Term Memory (LSTM)

حوزه‌های تخصصی:
تعداد بازدید : ۱۴ تعداد دانلود : ۱۱
This study explores whether combining Empirical Mode Decomposition (EMD) with machine learning models Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM)—can improve the accuracy of Bitcoin price volatility (VBTC) predictions. Utilizing daily Bitcoin price data from September 2011 to December 2024, the research, conducted using R software, compares the performance of hybrid models (EMD-ANN, EMD-RNN, EMD-LSTM) against standalone machine learning models and traditional time series methods like ARIMA. The results demonstrate that hybrid models significantly outperform their non-hybrid counterparts, with the EMD-RNN model achieving the highest accuracy, reducing Mean Absolute Error (MAE) by 95.76% and Root Mean Squared Error (RMSE) by 96.35%. The decomposition of VBTC into Intrinsic Mode Functions (IMFs) revealed distinct short-term and long-term volatility components, providing deeper insights into market behavior. The findings highlight the superiority of integrating EMD with machine learning for volatility forecasting, offering enhanced predictive accuracy and robustness. This research underscores the potential of advanced analytical techniques in improving risk management and investment strategies in highly volatile cryptocurrency markets.