Title :
Stock trend prediction using simple moving average supported by news classification
Author :
Lauren, Samuel ; Harlili, S.
Author_Institution :
Inf. Eng., Bandung Inst. of Technol., Bandung, Indonesia
Abstract :
The ability to predict stock trend is crucial for stock investors. Using daily time series data, one is able to predict the trend with the help of simple moving average technique. Unfortunately, stock trend is also affected by many factors, one of which is daily news. Daily news, particularly financial news have a great role in deciding stock trend. Each news has a sentiment value classified into positive, negative, and neutral sentiment that directly affects whether the trend goes up or down. It will be useful to combine simple moving average and news classification to predict stock trend more responsively. This paper uses machine learning using artificial neural network to combine the two aspects. The experiment in this paper uses approximately one year´s worth of stock data and financial news. Artificial neural network is able to combine simple moving average technique and news classification, and the result indicates that financial news can improve the prediction responsiveness.
Keywords :
information resources; learning (artificial intelligence); neural nets; pattern classification; stock markets; time series; artificial neural network; daily time series data; financial news; machine learning; news classification; simple moving average technique; stock trend prediction; Artificial neural networks; Feature extraction; Informatics; Learning (artificial intelligence); Machine learning algorithms; Market research; Time series analysis; artificial neural network; news classification; sentiment value; simple moving average; stock trend;
Conference_Titel :
Advanced Informatics: Concept, Theory and Application (ICAICTA), 2014 International Conference of
Conference_Location :
Bandung
Print_ISBN :
978-1-4799-6984-5
DOI :
10.1109/ICAICTA.2014.7005929
