Mohammad Sayadi; Meysam Omidi
Abstract
This study applied a prediction-based portfolio optimization model to explore the results of portfolio predicament in the Tehran Stock Exchange. To this aim, first, the data mining approach was used to predict the petroleum products and chemical industry using clustering stock market data. Then, some ...
Read More
This study applied a prediction-based portfolio optimization model to explore the results of portfolio predicament in the Tehran Stock Exchange. To this aim, first, the data mining approach was used to predict the petroleum products and chemical industry using clustering stock market data. Then, some effective factors, such as crude oil price, exchange rate, global interest rate, gold price, and S&P 500 index, were used to estimate each industry index using Radial Basis Function and Multi-Layer Perceptron neural networks. Finally, by comparing the validation ratios in a bullish market using K-Means, SOM, and Fuzzy C-means clustering algorithms, the best algorithm was employed to predict indicators for each industry. The sample was collected between December 15, 2008, and April 25, 2018. The results revealed that the Multi-Layer Perceptron algorithm had the highest accuracy and was the best option for portfolio predicament. However, the Fuzzy C-means algorithm produced the best clusters. Practical results showed that Sepahan oil and Kharg petrochemical stocks were the most important stocks in the short term while Kharg petrochemical, Fannavaran petrochemical, and Tehran oil refinery stocks made higher contributions in a stock portfolio in the medium- or long-term.
Afsaneh Kazemi Mehrabadi; Vahid Taghinezhad Omran; Mohammad Valipour Khatir; Saeed Rasekhi
Abstract
Forecasting industrial production is essential for efficient planning by managers. Although there are many statistical and mathematical methods for prediction, the use of intelligent algorithms with desirable features has made significant progress in recent years. The current study compared the accuracy ...
Read More
Forecasting industrial production is essential for efficient planning by managers. Although there are many statistical and mathematical methods for prediction, the use of intelligent algorithms with desirable features has made significant progress in recent years. The current study compared the accuracy of the Artificial Neural Networks (ANN) and Adaptive Nero-Fuzzy Inference System (ANFIS) approaches to assess the current state and predict the future state of industrial production. The seasonal dataset comprised the labor force, capital stock, human capital, trade openness, liquidity and credit financing to the industrial sector as input variables and value added of industrial production as the output variable for the period of 1988 to 2018. The dataset was used to forecast industrial production for Seasons of the year 2019 and 2020. The results showed that, while both are appropriate tools for forecasting industrial production, ANFIS had a lower the Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) than ANN. The findings of the research indicate that ANFIS is more effective in forecasting industrial production, which can help policymakers in planning and creating an effective strategy for the future.
Abstract
Forecasting energy price and consumption is essential in making effective managerial decisions and plans. While there are many sophisticated mathematical methods developed so far to forecast, some nature-based intelligent algorithms with desired characteristics have been developed recently. The main ...
Read More
Forecasting energy price and consumption is essential in making effective managerial decisions and plans. While there are many sophisticated mathematical methods developed so far to forecast, some nature-based intelligent algorithms with desired characteristics have been developed recently. The main objective of this research is short term forecasting of energy price and consumption in Iranian industrial sector using artificial intelligence including an Adaptive Neuro-Fuzzy Inference System (ANFIS) and an Artificial Neural Networks (ANN). The dataset contains monthly price and consumption of gas oil, petrol, and liquid petroleum gas in the period between March 1996 and March 2010. Based on dataset, energy price and consumption for 2011 and 2012 are forecasted. The results obtained utilizing the two methods show that while both are appropriate tools to forecast price and consumption, most of the time ANFIS has lower error than ANN in terms of the mean squared error criterion
