مطالب مرتبط با کلیدواژه

Prediction


۱.

پیش‌بینی بازده روزانه سهام شرکت های پذیرفته‌ شده در بورس اوراق بهادار تهران با استفاده از شبکه‌های عصبی مصنوعی

نویسنده:
منبع: فصلنامه تحقیقات مالی ۱۳۸۶ شماره ۲۴

کلیدواژه‌ها: بورس اوراق بهادار تهران پیش‎بینی exchange Tehran stock شبکه‏های عصبی مصنوعی الگوی یادگیری پس انتشار خطا Artificial Neural Error Back Networks Prediction Propagation Stock Return Behavior رفتار بازده سهام

حوزه های تخصصی:
تعداد بازدید : ۱۷۶۲
این مطالعه به بررسی پیش‌بینی‌پذیری رفتاربازده سهام شرکت‌های یذیرفته شده در بورس اوراق بهادار تهران وهمچنین انجام عمل پیش‌بینی بازده با استفاده از شبکه‌های عصبی مصنوعی می‌پردازد. به منظور انجام عمل پیش‌بینی بازده، در مرحله اول روند گذشته سری زمانی مربوط به شرکت‌ها و همچنین سه متغیر از متغیرهای تحلیل تکنیکی (شاخص سهام، حجم سهام مبادله شده و آخرین نرخ سهام در روز) برای مدت 5 سال(تیرماه 1377 لغایت 1382) مورد استفاده قرارگرفت وبا تغییر پارامترهای شبکه عصبی مصنوعی مدل بهینه جهت پیش‌بینی بازده روزانه سهام هر شرکت طراحی گردید. در مرحله دوم، پیش‌بینی بازده روزانه طی همان 5 سال صرفاً براساس اطلاعات گذشته یا روند گذشته سری زمانی انجام شد. در این پژوهش از شبکه عصبی مصنوعی با ساختار پرسپترون چند لایه (MLP) با توابع یادگیری متفاوت استفاده گردید. نتایج حاصل نشان‌دهنده آن است که: - رفتار سری زمانی بازده روزانه سهام شرکت‌ها یک فرآیند تصادفی نیست و دارای حافظه می‌باشد. - شبکه‌های عصبی مصنوعی توانایی پیش‌بینی بازده روزانه را با میزان خطای نسبتاً مناسبی دارند.
۲.

Creating Algorithmic Symbols to Enhance Learning English Grammar

نویسنده:
منبع: Research in English Education Volume ۳, Issue ۲ June ۲۰۱۸ 69-93

کلیدواژه‌ها: Prediction abstraction algorithm grammar symbols tenses

حوزه های تخصصی:
تعداد بازدید : ۴۱۵ تعداد دانلود : ۵۸۶
This paper introduces a set of English grammar symbols that the author has developed to enhance students’ understanding and consequently, application of the English grammar rules. A pretest-posttest control-group design was carried out in which the samples were students in two girls’ senior high schools (N=135, P ≤ 0.05) divided into two groups: the Treatment which received grammar lessons with grammar symbols; and the Control which received grammar lessons without the symbols. The experiment lasted for 30 hours spanned in three months. The statistical test revealed a significant higher gain scores for the Treatment group. Thus, the author strongly recommends using these symbols (or similar ones with the same characteristics) at least for two reasons. Firstly, students do not have to memorize all of them (72 tense symbols and 50 other symbols). That is, with just a few rules to learn, and then applying the existing algorithm, other symbols are easily shaped. Secondly, using these symbols enables teachers and students to have a general idea as to what to expect next because several grammatical rules and formulae can be predicted in advance.
۳.

Prediction the Return Fluctuations with Artificial Neural Networks' Approach(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۴, Issue ۲, Spring ۲۰۱۹ 103 - 114

کلیدواژه‌ها: Earning quality Artificial Neural Networks Prediction

حوزه های تخصصی:
تعداد بازدید : ۴۴۵ تعداد دانلود : ۳۸۱
Time changes of return, inefficiency studies performed and presence of effective factors on share return rate are caused development modern and intelligent methods in estimation and evaluation of share return in stock companies. Aim of this research is prediction of return using financial variables with artificial neural network approach. Therefore, the statistical population of this study includes 120 listed companies in Tehran stock securities during 2005 to 2017. Independent variables in this research are market variables (Earning quality, free cash flow) and dependent variable is share return. The obtained outputs from estimation of the artificial neural networks and results obtained from estimation, using of this method with evaluation scales concerning random amount and comparing it with adjusted R, we found that there is meaningful relation between the associated variables and return. However, such network has the least error than other networks.
۴.

Modeling the prediction of the Financial Behavior in Iranian Stock Market Investors with an Interpretive Structural Approach(مقاله علمی وزارت علوم)

نویسنده:
منبع: Iranian Journal of Finance, Volume ۲, Issue ۴, Autumn ۲۰۱۸ 1 - 26

کلیدواژه‌ها: Prediction financial behavior Investors Iran’s Stock Market Decision-making

حوزه های تخصصی:
تعداد بازدید : ۳۱۱ تعداد دانلود : ۴۰۸
Nowadays, predicting the financial behavior of investors plays a crucial role in decision-making and the financial policy-making process. This study is aimed at providing a paradigm to predict the financial behavior of investors in Iran’s stock market. 24 experts were interviewed to identify the variables, and 24 variables were identified. The interpretive structural paradigming was carried out using a self-interaction matrix based on the experts’ opinions. The MICMAC analysis has been used to identify the types of the variables. As findings of the study, a five-level paradigm was determined, in which environmental factors and the background of financial behavior on the fifth level were the most influential variables and also arbitrage, bias, and the perceptual mistake were the most impressible variables of the paradigm on the first level. MICMAC analysis of this study suggested that the variable of environmental factors had low dependence and high efficacy. Furthermore, psychological projection, perceptual mistake, arbitrage, and bias are dependent variables with high dependence and low efficacy. Other variables are mediator variables with high dependence and effectiveness.
۵.

Prediction of Natural Gas Price Using GMDH Type Neural Network:A Case Study of USA Market(مقاله علمی وزارت علوم)

نویسنده:
منبع: The International Journal of Humanities, Volume ۲۱, Issue ۳ (۲۰۱۴) 1-16
تعداد بازدید : ۲۴۱ تعداد دانلود : ۲۸۲
In this paper, a model based on GMDH Type Neural Network, is used to predict gas price in the spot market while using oil spot market price, gas spot market price, gas future market price, oil future market price and average temperature of the weather. The results suggest that GMDH Neural Network model, according to the Root Mean Squared Error (RMSE) and Direction statistics (Dstat) statistics are more effective than OLS method. Also, first lag of gas price in the future market is the most efficient variable in predicting gas price in spot market.
۶.

Modelling Crowdfunding Ensemble Learning Prediction(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۶, Issue ۳, Summer ۲۰۲۱ 408 - 423

کلیدواژه‌ها: Prediction Mathematical crowdfunding Entrepreneurship

حوزه های تخصصی:
تعداد بازدید : ۴۰۰ تعداد دانلود : ۲۲۴
Crowdfunding is a new technology-enabled innovative process that is changing the capital market space. Internet-based applications, particularly those related to Web 2.0, have had a significant impact on sectors of society such as education, business, and medicine. The goal of this research is to fill a gap in the literature on mathematical modelling and prediction of ensemble learning in order to evaluate crowdfunding projects. The Mathematical model determines the cost of funding for the entrepreneur and the return investors will receive per period. A correct financial model is essential in order to keep all three stakeholders involved in the long term. The results show the designed model improved performance in predicting the evaluation of success or failure of Crowdfunding projects.
۷.

Long Short-Term Memory Approach for Coronavirus Disease Predicti(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۲, Special Issue: The Importance of Human Computer Interaction: Challenges, Methods and Applications., ۲۰۲۰ 11 - 21

کلیدواژه‌ها: deep learning LSTM Prediction COVID-19 Recurrent Neural Network (RNN)

حوزه های تخصصی:
تعداد بازدید : ۳۷۶ تعداد دانلود : ۳۱۵
Corona Virus (COVID-19) is a major problem among people, and it causes suffering worldwide. Yet, the traditional prediction models are not yet suitably efficient in catching the fundamental expertise as they cannot visualize the difficulty in the health's representation problem areas. This paper states prediction mechanism that uses a model of deep learning called Long Short-Term Memory (LSTM). We have carried this model out on corona virus dataset that obtained from the records of infections, deaths, and recovery cases across the world. Furthermore, producing a dataset which includes features of geographic regions (temperature and humidity) that have experienced severe virus outbreaks, risk factors, spatio-temporal analysis, and social behavior of people, a predictive model can be developed for areas where the virus is likely to spread. However, the outcomes of this study are justifiable to alert the authorities and the people to take precautions.
۸.

Hybrid Weighted Random Forests Method for Prediction & Classification of Online Buying Customers(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۳, Issue ۲, ۲۰۲۱ 245 - 259

کلیدواژه‌ها: Weighted random forest Machine Learning Classification Prediction Online customer

حوزه های تخصصی:
تعداد بازدید : ۲۷۹ تعداد دانلود : ۱۵۹
Due to enchantment in network technology, the worldwide numbers of internet users are growing rapidly. Most of the internet users are using online purchasing from various sites. Due to new online shopping trends over the internet, the seller needs to predict the online customer’s choice. This field is a new area of research for machine learning researchers. A random forest (RF) machine learning method is a widely used classification method. It is mainly based on an ensemble of a single decision tree. Online e-commerce websites accumulate a massive quantity of data in large dimensions. A Random Forest is an efficient filter in high-dimensional data to reliably classify consumer behaviour factors. This research article mainly proposed an extension of the Random Forest classifier named “Weighted Random Forests” (wRF), which incorporates tree-level weights to provide much more accurate trees throughout the calculation as well as an assessment of vector relevance. The weighted random forest algorithm incorporates the C4.5 method named a “Hybrid Weighted Random Forest” (HWRF) to forecast online consumer purchasing behaviour. The experimental results influence the quality of the proposed method in the prediction of the behaviour of online buying customers over existing methods.
۹.

Capsule Network Regression Using Information Measures: An Application in Bitcoin Market(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۷, Issue ۱, Winter ۲۰۲۲ 37-48

کلیدواژه‌ها: deep learning Financial Market Prediction

حوزه های تخصصی:
تعداد بازدید : ۳۱۴ تعداد دانلود : ۱۴۹
Predicting financial markets has always been one of the most challenging issues, attracting the attention of many investors and researchers. In this regard, deep learning methods have been used a lot recently. Due to the desired results, such networks are always in development and progress. One of the networks that is being implemented in various fields is capsule network. The first time the classification capsule network was introduced, it was able to attract a lot of attention with its success on MNIST data 1 . In such networks, as in the other ones, the parameters are obtained by minimizing a loss function. In this paper, we first change the classification capsule network to a regression capsule network by modifying the last layer of the network. Then we use different information measures such as Kullnack-Leibler, Lin-Wang and Triangular information measures as a loss function, and compare their results with wellknown models including Artificial Neural Network (ANN), Convolutional Network (CNN) and Long Short-Term Memory (LSTM) as well as common used loss functions such as Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE). Using appropriate accuracy metrics, it is shown that the capsule network using triangular information measure is well able to predict the price of bitcoin for the medium and long term period including 10, 90 and 180 days.
۱۰.

A Data Envelopment Analysis Model to Provide a Dynamic Accounting Information System for Measuring the Financial Effectiveness of Management Accounting System(مقاله علمی وزارت علوم)

نویسنده:
منبع: Advances in Mathematical Finance and Application, Volume ۷, Issue ۱, Winter ۲۰۲۲ 169-186

کلیدواژه‌ها: deep learning Financial Market Prediction

حوزه های تخصصی:
تعداد بازدید : ۲۵۶ تعداد دانلود : ۱۹۶
The secret to achieving your organization's goals in complex and challenging environments is to make the right managerial and rational decisions. In this regard, the accounting information system as one of the sources of information for the decision of managers is of particular importance. Therefore, in order to achieve these goals, it is necessary to have an accounting information system with dynamic capabilities. The dynamic capability of the accounting information system (hidden variable) was measured by the observed variables of flexibility, continuous evaluation, continuous investment and system variability. Therefore, based on this argument, the aim of the present study is to provide a dynamic capability model of the accounting system based on the financial effectiveness of the management accounting system. Data envelopment analysis is a well-known methodology that is applied to evaluate the selected firms based on the most important features. The results of analysis of the proposed method on 86 companies listed on the Tehran Stock Exchange and analysis and analysis of data by structural equation modeling show that the dynamic capability of the accounting information system consists of (flexibility, continuous evaluation, continuous investment and system variability). The result indicate that the management accounting system is effective.
۱۱.

Mapping Grayscale Images to Colour Space Using Deep Learning(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۴, Security and Resource Management challenges for Internet of Things, ۲۰۲۲ 52 - 68

کلیدواژه‌ها: Convolutional Neural Networks (CNN) Convolution RGB CIELAB (Lab) deep neural networks Feature vector Prediction sampling

حوزه های تخصصی:
تعداد بازدید : ۲۷۰ تعداد دانلود : ۱۰۷
People are used to exploring grayscale images in their family albums but it is difficult to grasp the reality without colours. Luckily, with advancements in Machine Learning it has been possible to solve problems previously thought impossible. The authors aim to automatically colourize grayscale images using a subset of Machine Learning called Deep Learning. The system will be trained on an image dataset and given an input grayscale image the model will be able to assign aesthetically believable colours. A grayscale photograph has been provided; our approach solves the problem of visualizing a reasonable colour version of the grayscale picture. This issue is undoubtedly under controlled; therefore earlier methods to this problem have either counted majorly on user interaction or it leads to in unsaturated colourizations. The authors put forward a completely automatic approach that will try to produce realistic and vibrant colourizations as much as possible. The proposed system has been applied as a feed-forward in a Convolutional Neural Network and has been trained on over twenty thousand colour images currently.
۱۲.

A data Mining Approach using CNN and LSTM to Predict Divorce before Marriage(مقاله علمی وزارت علوم)

نویسنده:
منبع: International Journal of Web Research, Volume ۵, Issue ۱,Spring-Summer ۲۰۲۲ 88 - 95
تعداد بازدید : ۱۵۴ تعداد دانلود : ۱۰۳
Divorce will have destructive spiritual and material effects, and unfortunately, in this regard recent statistics have shown that solutions provided for its prevention and reduction have not been effective. One of the effective solutions to reduce divorce in society is to review the background of the couple, which can provide valuable experiences to experts, and used by experts and family counselors. In this article, a method has been proposed that uses data mining and deep learning to help family counselors to predict the outcome of marriage as a practical tool. Reviewing the background of thousands of couples will provide a model for the coupe behavior analysis. The primary data of this study was collected from the information of 35,000 couples registered in the National Organization for Civil Registration of Iran during 2018-2019. In the current work, we proposed a method to predict divorce by combining a convolutional neural network (CNN) and long short-term memory (LSTM). In this hybrid method, key features in a dataset are selected using CNN layers, and then predicted using LSTM layers with an accuracy of 99.67 percent. A comparison of the method used in this article and Multilayer Perceptron (MLP) and CNN suggests that it has a higher degree of accuracy.
۱۳.

Analysis of Diabetes disease using Machine Learning Techniques: A Review(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۵, Issue ۴, ۲۰۲۳ 139 - 159

کلیدواژه‌ها: Machine Learning diabetes Classifiers Prediction Classification

حوزه های تخصصی:
تعداد بازدید : ۷۷ تعداد دانلود : ۶۱
Diabetes is a type of metabolic disorder with a high level of blood glucose. Due to the high blood sugar, the risk of heart-related diseases like heart attack and stroke got increased. The number of diabetic patients worldwide has increased significantly, and it is considered to be a major life-threatening disease worldwide. The diabetic disease cannot be cured but it can be controlled and managed by timely detection. Artificial Intelligence (AI) with Machine Learning (ML) empowers automatic early diabetes detection which is found to be much better than a manual method of diagnosis. At present, there are many research papers available on diabetes detection using ML techniques. This article aims to outline most of the literature related to ML techniques applied for diabetes prediction and summarize the related challenges. It also talks about the conclusions of the existing model and the benefits of the AI model. After a thorough screening method, 74 articles from the Scopus and Web of Science databases are selected for this study. This review article presents a clear outlook of diabetes detection which helps the researchers work in the area of automated diabetes prediction.
۱۴.

An Accurate Prediction Framework for Cardiovascular Disease Using Convolutional Neural Networks(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۶, Issue ۱, ۲۰۲۴ 27 - 43

کلیدواژه‌ها: Deep-Learning CNN Heart-Disease Prediction Cardiovascular disease Accuracy

حوزه های تخصصی:
تعداد بازدید : ۱۰۵ تعداد دانلود : ۶۸
Cardiovascular-Diseases (CVD) are a principal cause of death worldwide. According to the World-Health-Organization (WHO), cardiovascular illnesses kill 20 million people annually. Predictions of heart-disease can save lives or take them, depending on how precise they are. The virus has rendered conventional methods of disease anticipation ineffective. Therefore, a unified system for accurate illness prediction is required. The study of disease diagnosis and identification has reached new heights thanks to artificial intelligence. With the right kind of training and testing, deep learning has quickly become one of the most cutting-edge, reliable, and sustaining technologies in the field of medicine. Using the University of California Irvine (UCI) machine-learning (ML) heart disease dataset, we propose a Convolutional-Neural-Network (CNN) for early disease prediction. There are 14 primary characteristics of the dataset that are being analyzed here. Accuracy and confusion matrix are utilized to verify several encouraging outcomes. Irrelevant features in the dataset are eliminated utilizing Isolation Forest, and the data is also standardized to enhance accuracy. Accuracy of 98% was achieved by employing a deep learning technique.
۱۵.

Chronic Kidney Disease Risk Prediction Using Machine Learning Techniques(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۶, Issue ۱, ۲۰۲۴ 118 - 134

کلیدواژه‌ها: Machine Learning CKD Prediction SVM RF Data Analysis

حوزه های تخصصی:
تعداد بازدید : ۱۲۰ تعداد دانلود : ۷۱
In healthcare, a diagnosis is reached after a thorough physical assessment and analysis of the patient's medicinal history, as well as the utilization of appropriate diagnostic tests and procedures. 1.7 million People worldwide lose their lives every year due to complications from chronic kidney disease (CKD). Despite the availability of other diagnostic approaches, this investigation relies on machine learning because of its superior accuracy. Patients with chronic kidney disease (CKD) who experience health complications like high blood pressure, anemia, mineral-bone disorder, poor nutrition, acid abnormalities, and neurological-complications may benefit from timely and exact recognition of the disease's levels so that they can begin treatment with the most effective medications as soon as possible. Several works have been investigated on the early recognition of CKD utilizing machine-learning (ML) strategies. The accuracy of stage anticipations was not their primary concern. Both binary and multiclass classification methods have been used for stage anticipation in this investigation. Random-Forest (RF), Support-Vector-Machine (SVM), and Decision-Tree (DT) are the prediction models employed. Feature-selection has been carried out through scrutiny of variation and recursive feature elimination utilizing cross-validation (CV). 10-flod CV was utilized to assess the models. Experiments showed that RF utilizing recursive feature removal with CV outperformed SVM and DT.
۱۶.

An Intelligent Heart Disease Prediction by Machine Learning Using Optimization Algorithm(مقاله علمی وزارت علوم)

نویسنده:
منبع: Journal of Information Technology Management , Volume ۱۶, Issue ۱, ۲۰۲۴ 167 - 181

کلیدواژه‌ها: Optimization algorithm Cardiovascular disease Prediction Gradient Descent Machine Learning Neural Networks deep learning

حوزه های تخصصی:
تعداد بازدید : ۱۷۲ تعداد دانلود : ۱۳۸
Heart and circulatory system diseases are often referred to as cardiovascular disease (CVD). The health and efficiency of the heart are crucial to human survival. CVD has become a primary cause of demise in recent years. According to data provided by the World-Health-Organization (WHO), CVD were conscientious for the deaths of 18.6M people in 2017. Biomedical care, healthcare, and disease prediction are just few of the fields making use of cutting-edge skills like machine learning (ML) and deep learning (DL). Utilizing the CVD dataset from the UCI Machine-Repository, this article aims to improve the accuracy of cardiac disease diagnosis. Improved precision and sensitivity in diagnosing heart disease by the use of an optimization algorithm is possible. Optimization is the process of evaluating a number of potential answers to a problem and selecting the best one. Support-Machine-Vector (SVM), K-Nearest-Neighbor (KNN), Naïve-Bayes (NB), Artificial-Neural-Network (ANN), Random-Forest (RF), and Gradient-Descent-Optimization (GDO) are just some of the ML strategies that have been utilized. Predicting Cardiovascular Disease with Intelligence, the best results may be obtained from the set of considered classification techniques, and this is where the GDO approach comes in. It has been evaluated and found to have an accuracy of 99.62 percent. The sensitivity and specificity were likewise measured at 99.65% and 98.54%, respectively. According to the findings, the proposed unique optimized algorithm has the potential to serve as a useful healthcare examination system for the timely prediction of CVD and for the study of such conditions.
۱۷.

A method based on wavelet denoising and DTW algorithm for stock price pattern recognition in Tehran stock exchange(مقاله علمی وزارت علوم)

نویسنده:
منبع: اقتصاد مقداری سال ۲۱ بهار ۱۴۰۳ شماره ۱ (پیاپی ۸۰) 1 - 28

کلیدواژه‌ها: Dynamic time warping wavelet denoising Stock Prediction

حوزه های تخصصی:
تعداد بازدید : ۵۳ تعداد دانلود : ۴۴
The main reason for people investing in the stock market is to make a profit, which requires accurate information about the stock market, price changes and predicting its future trend. Therefore, investors need powerful and reliable tools for forecasting Stock prices in the future. The main purpose of this study is to present a method based on wavelet denoising and dynamic time warping to identify the stock price pattern in the Tehran Stock Exchange. In this regard, first, using the wavelet denoising preprocessing step, noise is removed from the stock price time series, and then the extracted data is used as input to the dynamic time warping prediction model. MATLAB software version 9.11 was used to analyze the research data. The statistical population of the present study includes 3 shares among the shares of steel industry companies of Tehran Stock Exchange. The research was conducted in the period 1395 to 1398. The results show that the predictions obtained from the dynamic time warping method equipped with the wavelet denoising preprocessing step in comparison with the predictions obtained from the dynamic time warping method without the wavelet denoising preprocessing step in all three shares studied, have been associated with much less accuracy and error.