TY - GEN
T1 - Prediction of the closing price in the Dubai financial market
T2 - 3rd MEC International Conference on Big Data and Smart City, ICBDSC 2016
AU - Aldarmaki, Noura
AU - Mohamed, Elfadil A.
AU - Almansouri, Noura
AU - Ahmed, Ibrahim Elsiddig
AU - Zaki, Nazar
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/4/26
Y1 - 2016/4/26
N2 - Closing prices of the financial stock market change daily at the end of each session. These changes happen because of many factors that affect the prices of the stocks. This study attempts to accurately predict closing prices by applying a data mining approach and investigate and identify the most influential factors of Dubai Financial Stock Market prices. The main objective of this study is to help investors plan their future investment opportunities well. Two methods are used in this study: supervised and unsupervised algorithms. The results obtained have shown that the model can predict the closing price using the classification algorithm with accuracy greater than 92% and that the regression algorithm succeeded in predicting the stock prices with a correlation coefficient equal to 0.8889.
AB - Closing prices of the financial stock market change daily at the end of each session. These changes happen because of many factors that affect the prices of the stocks. This study attempts to accurately predict closing prices by applying a data mining approach and investigate and identify the most influential factors of Dubai Financial Stock Market prices. The main objective of this study is to help investors plan their future investment opportunities well. Two methods are used in this study: supervised and unsupervised algorithms. The results obtained have shown that the model can predict the closing price using the classification algorithm with accuracy greater than 92% and that the regression algorithm succeeded in predicting the stock prices with a correlation coefficient equal to 0.8889.
KW - Artificial Neural Networks (ANN)
KW - Financial Market (DFM)
KW - Genetic Algorithms (GA)
KW - Regression analysis
KW - Voting Feature Intervals (VFI)
KW - classification method
KW - data mining
KW - dividend yield (DY)
UR - http://www.scopus.com/inward/record.url?scp=84973568774&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84973568774&partnerID=8YFLogxK
U2 - 10.1109/ICBDSC.2016.7460345
DO - 10.1109/ICBDSC.2016.7460345
M3 - Conference contribution
AN - SCOPUS:84973568774
T3 - 2016 3rd MEC International Conference on Big Data and Smart City, ICBDSC 2016
SP - 72
EP - 78
BT - 2016 3rd MEC International Conference on Big Data and Smart City, ICBDSC 2016
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 15 March 2016 through 16 March 2016
ER -