随着国民生活水平的提高,越来越多的人投身于股票市场.为了科学有效地量化选股,通过将量化投资、深度学习及文本分析进行有机结合,来建立量化选股模型.首先,通过文本分析筛选出基本面利好的股票;然后,通过长短期记忆(long-short term me...随着国民生活水平的提高,越来越多的人投身于股票市场.为了科学有效地量化选股,通过将量化投资、深度学习及文本分析进行有机结合,来建立量化选股模型.首先,通过文本分析筛选出基本面利好的股票;然后,通过长短期记忆(long-short term memory,LSTM)选出预测准确度良好的股票;最后,预测所选出的股票在未来几天的股价趋势.在实证分析方面,通过本模型对部分股票进行运算,选取预测效果较好的股票:赢合科技.展开更多
针对中证1000成分股的投资策略构建,提出了基于支持向量机的多因子融合量价数据选股策略,应用于实时或模拟市场数据的回测中,以评估策略的有效性。本文对基于支持向量机的多因子选股模型进行改进,将量价数据融合到选股模型中,在多因子...针对中证1000成分股的投资策略构建,提出了基于支持向量机的多因子融合量价数据选股策略,应用于实时或模拟市场数据的回测中,以评估策略的有效性。本文对基于支持向量机的多因子选股模型进行改进,将量价数据融合到选股模型中,在多因子选股模型筛选出的股票基础上,进一步融合量价数据再次筛选,以期望获得更优的收益。回测结果表明,加入量价数据与未加入量价数据的模型对比,策略收益率提高了4.83%,策略年化收益率提高了11.43%,策略累积收益率与夏普比率显著优于多因子选股策略,最大回撤比之减小或者略高,预测涨跌更为接近实际股票涨跌趋势。实验结果表明:基于支持向量机的多因子融合量价数据选股策略应用在量化投资上,是十分有效的。In response to the construction of investment strategy for the constituent stocks of China Securities 1000, a stock selection strategy with the fusion of data of multi-factor, volume and price based on support vector machine is proposed which is applied to real-time or simulated market data backtesting, in order to evaluate the effectiveness of the strategy. We improve the multi-factor model of stock selection based on support vector machine, integrate the volume and price data into the model of stock selection, and further fuse the volume and price data to screen the stocks selected by the multi-factor model of stock selection to obtain more optimal returns. According to the backtest results, compared with the model with or without the addition of volume and price data and the model, the strategy return rate increases by 4.83%, the strategy annual return rate increases by 11.43%, the strategy cumulative return to sharp ratio is significantly better than that of the multi-factor stock selection strategy, and the maximum retracement ratio decreases or is slightly higher. The improved forecast moves more closely to the actual trend of stock movements. The results show that the strategy of stock selection with the fusion of data of multi-factor volume and price based on support vector machine is very effective in quantitative investment.展开更多
随着金融计算机领域的迅猛发展,量化投资正在扮演越来越重要的角色。多因子选股模型作为量化投资领域的重要组成部分,是量化投资策略选取优质股票组合的有效工具。本文以沪深300成分股为研究对象,综合考虑了成长类、技术类、价值类、情...随着金融计算机领域的迅猛发展,量化投资正在扮演越来越重要的角色。多因子选股模型作为量化投资领域的重要组成部分,是量化投资策略选取优质股票组合的有效工具。本文以沪深300成分股为研究对象,综合考虑了成长类、技术类、价值类、情绪类以及动量类对股价有影响的因子,运用因子暴露分析、相关系数以及因子IC确定能够显著影响股票收益率的因子,再建立具有最优参数的核函数支持向量机模型,选取2010年1月1日到2023年1月1日作为时间区间进行训练与回测。得出结论:沪深300成分股的有效因子为市值、股本、换手率、ROE和PE;由高斯核函数支持向量机模型选股策略构建的投资组合策略能够保持投资组合的多样性,具有较高的风险回报能力,且收益较为稳定,能够跑赢大盘,证明了模型的有效性。With the rapid development of the financial computer field, quantitative investment is playing an increasingly important role. The multi factor stock selection model, as an important component of quantitative investment, is an effective tool for selecting high-quality stock portfolios in quantitative investment strategies. This article takes the 300 constituent stocks of Shanghai and Shenzhen as the research object, comprehensively considers the factors that affect stock prices, including growth, technology, value, emotion, and momentum. Factor exposure analysis, correlation coefficients, and factor IC are used to determine the factors that can significantly affect stock returns. Then, a kernel function support vector machine model with the optimal parameters is established, selecting January 1, 2010 to January 1, 2023 as the time interval for training and backtesting. Conclusion: The effective factors of the 300 constituent stocks in Shanghai and Shenzhen are market value, share capital, turnover rate, ROE, and PE;The investment portfolio strategy constructed by Gaussian kernel support vector machine model stock selection strategy can maintain the diversity of the investment portfolio, have high risk return ability, and stable returns, which can outperform the market, proving the effectiveness of the model.展开更多
本文基于中国A股市场数据,选取四个节点网络指标构建了网络因子,将其与传统的Fama-French三因子模型相结合,提出了新的四因子选股模型。实证研究表明,该模型比三因子模型更能解释收益率的变动。基于四因子模型进行的选股策略的回测结果...本文基于中国A股市场数据,选取四个节点网络指标构建了网络因子,将其与传统的Fama-French三因子模型相结合,提出了新的四因子选股模型。实证研究表明,该模型比三因子模型更能解释收益率的变动。基于四因子模型进行的选股策略的回测结果显示,网络因子构建的投资组合在收益率、风险和最大回撤率等方面均优于上证A股指数。This paper, based on data from China’s A-share market, constructs a network factor using four network indicators and combines it with the traditional Fama-French three-factor model to propose a new four-factor stock selection model. Empirical research shows that this model can better explain variations in returns compared to the three-factor model. Back-testing results of the stock selection strategy based on the four-factor model indicate that the investment portfolio constructed with the network factor outperforms the Shanghai A-share index in terms of returns, risk, and maximum drawdown rate.展开更多
文摘随着国民生活水平的提高,越来越多的人投身于股票市场.为了科学有效地量化选股,通过将量化投资、深度学习及文本分析进行有机结合,来建立量化选股模型.首先,通过文本分析筛选出基本面利好的股票;然后,通过长短期记忆(long-short term memory,LSTM)选出预测准确度良好的股票;最后,预测所选出的股票在未来几天的股价趋势.在实证分析方面,通过本模型对部分股票进行运算,选取预测效果较好的股票:赢合科技.
文摘针对中证1000成分股的投资策略构建,提出了基于支持向量机的多因子融合量价数据选股策略,应用于实时或模拟市场数据的回测中,以评估策略的有效性。本文对基于支持向量机的多因子选股模型进行改进,将量价数据融合到选股模型中,在多因子选股模型筛选出的股票基础上,进一步融合量价数据再次筛选,以期望获得更优的收益。回测结果表明,加入量价数据与未加入量价数据的模型对比,策略收益率提高了4.83%,策略年化收益率提高了11.43%,策略累积收益率与夏普比率显著优于多因子选股策略,最大回撤比之减小或者略高,预测涨跌更为接近实际股票涨跌趋势。实验结果表明:基于支持向量机的多因子融合量价数据选股策略应用在量化投资上,是十分有效的。In response to the construction of investment strategy for the constituent stocks of China Securities 1000, a stock selection strategy with the fusion of data of multi-factor, volume and price based on support vector machine is proposed which is applied to real-time or simulated market data backtesting, in order to evaluate the effectiveness of the strategy. We improve the multi-factor model of stock selection based on support vector machine, integrate the volume and price data into the model of stock selection, and further fuse the volume and price data to screen the stocks selected by the multi-factor model of stock selection to obtain more optimal returns. According to the backtest results, compared with the model with or without the addition of volume and price data and the model, the strategy return rate increases by 4.83%, the strategy annual return rate increases by 11.43%, the strategy cumulative return to sharp ratio is significantly better than that of the multi-factor stock selection strategy, and the maximum retracement ratio decreases or is slightly higher. The improved forecast moves more closely to the actual trend of stock movements. The results show that the strategy of stock selection with the fusion of data of multi-factor volume and price based on support vector machine is very effective in quantitative investment.
文摘随着金融计算机领域的迅猛发展,量化投资正在扮演越来越重要的角色。多因子选股模型作为量化投资领域的重要组成部分,是量化投资策略选取优质股票组合的有效工具。本文以沪深300成分股为研究对象,综合考虑了成长类、技术类、价值类、情绪类以及动量类对股价有影响的因子,运用因子暴露分析、相关系数以及因子IC确定能够显著影响股票收益率的因子,再建立具有最优参数的核函数支持向量机模型,选取2010年1月1日到2023年1月1日作为时间区间进行训练与回测。得出结论:沪深300成分股的有效因子为市值、股本、换手率、ROE和PE;由高斯核函数支持向量机模型选股策略构建的投资组合策略能够保持投资组合的多样性,具有较高的风险回报能力,且收益较为稳定,能够跑赢大盘,证明了模型的有效性。With the rapid development of the financial computer field, quantitative investment is playing an increasingly important role. The multi factor stock selection model, as an important component of quantitative investment, is an effective tool for selecting high-quality stock portfolios in quantitative investment strategies. This article takes the 300 constituent stocks of Shanghai and Shenzhen as the research object, comprehensively considers the factors that affect stock prices, including growth, technology, value, emotion, and momentum. Factor exposure analysis, correlation coefficients, and factor IC are used to determine the factors that can significantly affect stock returns. Then, a kernel function support vector machine model with the optimal parameters is established, selecting January 1, 2010 to January 1, 2023 as the time interval for training and backtesting. Conclusion: The effective factors of the 300 constituent stocks in Shanghai and Shenzhen are market value, share capital, turnover rate, ROE, and PE;The investment portfolio strategy constructed by Gaussian kernel support vector machine model stock selection strategy can maintain the diversity of the investment portfolio, have high risk return ability, and stable returns, which can outperform the market, proving the effectiveness of the model.
文摘本文基于中国A股市场数据,选取四个节点网络指标构建了网络因子,将其与传统的Fama-French三因子模型相结合,提出了新的四因子选股模型。实证研究表明,该模型比三因子模型更能解释收益率的变动。基于四因子模型进行的选股策略的回测结果显示,网络因子构建的投资组合在收益率、风险和最大回撤率等方面均优于上证A股指数。This paper, based on data from China’s A-share market, constructs a network factor using four network indicators and combines it with the traditional Fama-French three-factor model to propose a new four-factor stock selection model. Empirical research shows that this model can better explain variations in returns compared to the three-factor model. Back-testing results of the stock selection strategy based on the four-factor model indicate that the investment portfolio constructed with the network factor outperforms the Shanghai A-share index in terms of returns, risk, and maximum drawdown rate.
