Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy

Stock market transaction is one of the most popular investments activities. There are many conventional techniques being used as a tool to predict the behaviour of the stock market, and these include technical and fundamental analysis. Recently, Artificial Intelligence (AI) such as Artificial Neural...

Full description

Saved in:

Bibliographic Details
Main Author:	Mohd. Yunos, Zuriahati
Format:	Thesis
Language:	English
Published:	2006
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/5508/1/NoorKhaidaWatiMFS2006.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.5508
record_format	uketd_dc
spelling	my-utm-ep.55082018-03-10T12:10:59Z Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy 2006-06 Mohd. Yunos, Zuriahati QA75 Electronic computers. Computer science Stock market transaction is one of the most popular investments activities. There are many conventional techniques being used as a tool to predict the behaviour of the stock market, and these include technical and fundamental analysis. Recently, Artificial Intelligence (AI) such as Artificial Neural Networks (ANN), Genetic Algorithms (GA), Fuzzy Logic (FL) and Rough Set (RS) are widely used by the researchers due to their ability to predict the behaviour of the stock market efficiently. In this research, a comprehensive pre-processing data modeling of stock market is developed to acquire granular informations that represent the behaviour of the data that is to be fed to the classifier. The pre-process methodology includes splitting, scaling, normalization, feature selection, and follows by the Ten-Fold Cross Validation method as a benchmark for estimating the predictive accuracy and effectiveness of splitting and selecting the input data. Daily data of Kuala Lumpur Composite Index (KLCI) is captured and analyzed, and it is found that the movements of the Indices are unstable; hence the forecasting process becomes difficult. Therefore, in this study, a Hybrid Neurofuzzy approached using Adaptive Neurofuzzy Inference System (ANFIS) model is suggested to predict the behaviour of the Indices. Furthermore, technical indicator such as moving average, relative strength index, stochastic indicator and price of change are used to analyze the data, and these parameters become input to ANFIS. Root Mean Square Error (RMSE) and Mean Absolute Percentage of Error (MAPE) are chosen to measure the prediction accuracy. In addition, to verify the effectiveness of the ANFIS model, the economic related factors as well as natural disaster are also provided. These factors such as tsunami, human actions, politics and even psychological have influenced on stock movement, thus compliance with the proposed model The results are promising and conforming with the actual price of Composite Index at Bursa Saham Malaysia. 2006-06 Thesis http://eprints.utm.my/id/eprint/5508/ http://eprints.utm.my/id/eprint/5508/1/NoorKhaidaWatiMFS2006.pdf application/pdf en public masters Universiti Teknologi Malaysia, Faculty of Computer Science and Information System Faculty of Computer Science and Information System
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA75 Electronic computers Computer science
spellingShingle	QA75 Electronic computers Computer science Mohd. Yunos, Zuriahati Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy
description	Stock market transaction is one of the most popular investments activities. There are many conventional techniques being used as a tool to predict the behaviour of the stock market, and these include technical and fundamental analysis. Recently, Artificial Intelligence (AI) such as Artificial Neural Networks (ANN), Genetic Algorithms (GA), Fuzzy Logic (FL) and Rough Set (RS) are widely used by the researchers due to their ability to predict the behaviour of the stock market efficiently. In this research, a comprehensive pre-processing data modeling of stock market is developed to acquire granular informations that represent the behaviour of the data that is to be fed to the classifier. The pre-process methodology includes splitting, scaling, normalization, feature selection, and follows by the Ten-Fold Cross Validation method as a benchmark for estimating the predictive accuracy and effectiveness of splitting and selecting the input data. Daily data of Kuala Lumpur Composite Index (KLCI) is captured and analyzed, and it is found that the movements of the Indices are unstable; hence the forecasting process becomes difficult. Therefore, in this study, a Hybrid Neurofuzzy approached using Adaptive Neurofuzzy Inference System (ANFIS) model is suggested to predict the behaviour of the Indices. Furthermore, technical indicator such as moving average, relative strength index, stochastic indicator and price of change are used to analyze the data, and these parameters become input to ANFIS. Root Mean Square Error (RMSE) and Mean Absolute Percentage of Error (MAPE) are chosen to measure the prediction accuracy. In addition, to verify the effectiveness of the ANFIS model, the economic related factors as well as natural disaster are also provided. These factors such as tsunami, human actions, politics and even psychological have influenced on stock movement, thus compliance with the proposed model The results are promising and conforming with the actual price of Composite Index at Bursa Saham Malaysia.
format	Thesis
qualification_level	Master's degree
author	Mohd. Yunos, Zuriahati
author_facet	Mohd. Yunos, Zuriahati
author_sort	Mohd. Yunos, Zuriahati
title	Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy
title_short	Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy
title_full	Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy
title_fullStr	Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy
title_full_unstemmed	Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy
title_sort	pemodelan data indeks komposit kuala lumpur menggunakan neurofuzzy
granting_institution	Universiti Teknologi Malaysia, Faculty of Computer Science and Information System
granting_department	Faculty of Computer Science and Information System
publishDate	2006
url	http://eprints.utm.my/id/eprint/5508/1/NoorKhaidaWatiMFS2006.pdf
_version_	1747814601244803072

Pemodelan data indeks komposit Kuala Lumpur menggunakan neurofuzzy

Similar Items