基于改进随机森林算法的股票趋势预测
|
摘要
针对目前股票趋势预测中随机森林算法无法对特征进行选择问题,提出一种离散二进制粒子群算法与随机森林算法相结合的混合算法。计算不同的技术指标作为输入特征,每一个特征都有4个不同时间跨度:3,5,10,15天,然后用离散二进制粒子群算法对特征进行优化选择。采用苹果公司、亚马逊公司、微软公司的股票历史数据进行仿真实验,实验结果与随机森林算法相比,准确率显著提高,苹果公司股票趋势预测的准确率达到93.0%,亚马逊公司达到90.5%,微软公司达到90.4%。
In view of the problem that the random forest algorithm can't select features in current stock trend forecasting, a hybrid algorithm combining discrete binary particle swarm optimization and random forest algorithm is proposed. Different technical indicators are calculated as input features. Each feature has four different time spans: 3, 5, 10, and 15 days, then use discrete binary particle swarm optimization algorithm to optimize the features. The simulation results were carried out using the stock historical data of Apple, Amazon and Microsoft and compared with the random forest algorithm is significantly improved. The accuracy of Apple's stock trend forecast reached 93.0%, and Amazon's reached 90.5%, Microsoft reached 90.4%.
In view of the problem that the random forest algorithm can't select features in current stock trend forecasting, a hybrid algorithm combining discrete binary particle swarm optimization and random forest algorithm is proposed. Different technical indicators are calculated as input features. Each feature has four different time spans: 3, 5, 10, and 15 days, then use discrete binary particle swarm optimization algorithm to optimize the features. The simulation results were carried out using the stock historical data of Apple, Amazon and Microsoft and compared with the random forest algorithm is significantly improved. The accuracy of Apple's stock trend forecast reached 93.0%, and Amazon's reached 90.5%, Microsoft reached 90.4%.
引文
[1] KUMAR D, MEGHWANI S S, THAKUR M. Proximal support vector machine based hybrid prediction models for trend forecasting in financial markets[J]. Journal of Computational Science, 2016, 17:1-13.
[2] ZOU Z B, PENG H, LUO L K. The application of random forest in finance[J]. Applied Mechanics & Materials, 2015, 740:947-951.
[3] PATEL J, SHAH S, THAKKAR P, et al. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques[J]. Expert Systems with Applications, 2015, 42(1):259-268.
[4] KARA Y, ACAR BOYACIOGLU M, BAYKAN ? K. Predicting direction of stock price index movement using artificial neural networks and support vector machines[J]. Expert Systems with Applications, 2011, 38(5):5311-5319.
[5] KHAIADEM L, SAHA S, DEY S R. Predicting the direction of stock market prices using random forest[J]. Computing Research Repository, 2016, 3(1):1605-1624.
[6] 刘敏, 郎荣玲, 曹永斌. 随机森林中树的数量[J]. 计算机工程与应用, 2015, 51(5):126-131.
[2] ZOU Z B, PENG H, LUO L K. The application of random forest in finance[J]. Applied Mechanics & Materials, 2015, 740:947-951.
[3] PATEL J, SHAH S, THAKKAR P, et al. Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques[J]. Expert Systems with Applications, 2015, 42(1):259-268.
[4] KARA Y, ACAR BOYACIOGLU M, BAYKAN ? K. Predicting direction of stock price index movement using artificial neural networks and support vector machines[J]. Expert Systems with Applications, 2011, 38(5):5311-5319.
[5] KHAIADEM L, SAHA S, DEY S R. Predicting the direction of stock market prices using random forest[J]. Computing Research Repository, 2016, 3(1):1605-1624.
[6] 刘敏, 郎荣玲, 曹永斌. 随机森林中树的数量[J]. 计算机工程与应用, 2015, 51(5):126-131.