欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
金融市场股票的价格预测是投资者们关心的热门问题，随着股票数据规模以及样本维数的日益庞大，人们对于股票预测算法在保证准确之外的预测速度也提出了更高的要求。在最小二乘支持向量机（LSSVM）股票预测算法的基础上，提出一种适宜支持向量机的GPU并行计算模型。实验证明，新方法不仅可以保证预测的精度，而且可以大大缩短预测时间。该方法可以广泛运用到金融领域的大规模数据处理以及预测中，具有较高的应用价值。
英文摘要：
Stocks price forecast in financial market is the top concern of the investors. Along with the increasingly bulky stock data size and dimensions of sample, people pursue bigber requirement in prediction speed of stock prediction algorithm other than its accuracy. This paper, based on least squares support vector machine （LSSVM） stock prediction algorithm, presents a GPU＇ s parallel computing model suitable for support vector machine. Experiments show that the new method can guarantee the accuracy of the prediction, and can also reduce the prediction time remarkably. This method can be widely applied to large-scale data processing and forecasting in financial sector, and has high applied value.
同期刊论文项目
同项目期刊论文
Approximation quality of fuzzy preference rough sets and its application in radio signal recognition
Properties of fuzzy induced ordered weighted averaging aggregation operator and its application in d
Implication Operator on the Set of ∨-Irreducible Element in the Linguistic Truth-Valued Intuitionist
期刊信息
位置：