文章基本信息

标题：Implementation of Stock Market Prediction
本地全文：下载
作者：Tejinder Singh ; Er. Mohit
期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：9
DOI：10.15680/IJIRCCE.2015. 0309132
出版社：S&S Publications
摘要：Today the topic based on Stock Market Prediction is on peak as per as the research field is concerned..As we know in social media micro logging service has been grown famous which provides the users with number ofreal time messages. In previous methods we used a factorization machine (FM) to predict stock market trends. FMalleviates the effect of dimensionality as well as captures aspects of basic linguistics..The accuracy of the existingmodel is not sufficient. The accuracy has been recorded at 81 percent, which means there is higher probability of thewrong predictions. Unlike many existing approaches we proposed a novel kind of model which uses a technology ofArtificial Neural network (ANN) with history of stocks data for stock market prediction. The data is used to train theartificial neural network (ANN) which is implemented via Neuroph, an open source library for Artificial Neuralnetwork implementation in java. Experiments on real-world data show that our new can achieve 90% accuracy and getsignificantly more profit than state-of-the-art models
关键词：NLP; Neuroph; stock market prediction; Artificial Neural network; factorization machines; KDT.