【专题研究】基于XGBoost模型的智能选股策略

xgboost
专题报告
策略分享
机器学习
标签: #<Tag:0x00007f609fcc7c28> #<Tag:0x00007f609fcc7ae8> #<Tag:0x00007f609fcc79a8> #<Tag:0x00007f609fcc7868>

(iQuant) #1

上篇报告介绍了集成学习里Bagging方法的代表算法随机森林,本文将着眼于另一种集成学习方法:Boosting,并深入介绍Boosting里的“王牌” XGBoost 模型。最后,以一个实例介绍XGBoost模型在智能选股方面的应用。


$$目录$$
1、Boosting V.S. Bagging
2、XGBoost原理解析
 2.1 XGBoost的主要原理
 2.2 XGBoost的重要参数
 2.3 XGBoost的优势
 2.4 其他
3、XGBoost智能选股


1、Boosting V.S. Bagging

作为集成学习的两大分支,Boosting和Bagging都秉持着“三个臭皮匠顶个诸葛亮”的想法,致力于将单个弱学习器组合成为一个强学习器。他们的不同主要在组合方式上:

Bagging如上篇报告介绍的,采用bootstrap随机抽样从整体数据集中得到很多个小数据集(小袋),用每一个小数据集分别并列训练弱学习器,最后采纳投票或者取均值的方式得到强学习器。

而Boosting的想法是加强,用整体数据集训练出第一个弱学习器后,在此基础上采用调整权值或者拟合残差的方法降低数据集的损失,最后采用加权平均或者加法原理得到强学习器。Boosting每一步的优化都要在得到上一步弱学习器的基础上进行,是一种“串行”的方法。


$$图1:Boosting 和 Bagging 示意$$

这两种方法的主要区别如下:

方法 Boosting Bagging
结构 串行 并行
训练集 依赖 独立
作用 减少bias 减少variance

2、XGBoost原理解析

2.1 XGBoost的主要原理

XGBoost(eXtreme Gradient Boosting)全名为极端梯度提升,是一种Boosting集成算法。它通过最小化损失函数(目标函数)训练单个弱学习器,然后计算得出残差,用残差集再去训练新的弱学习器,目的在于让样本的损失变得更小。在所有的弱学习器训练完成后,将得分加总得到强学习器的得分。

XGBoost的创新之处在于在单纯的损失函数:$ \sum_{i=1}^{n}L(y_i,\hat{y_i})$ 基础上增加了惩罚项:$ \sum_{k=1}^{K}\Omega(f_k)$,降低模型的复杂度,从而避免过拟合问题。


$$图2:XGBoost算法流程$$

XGBoost 的思想可以用一个通俗的例子解释,假如某人有170厘米身高,我们首先用160厘米去拟合,发现残差有10厘米,这时我们用6厘米去拟合剩下的残差,发现残差还有4厘米,第三轮我们用3厘米拟合剩下的残差,残差就只有1厘米了。如果迭代轮数还没有完,可以继续迭代下去,每一轮迭代,拟合的身高残差都会减小。

2.2 XGBoost的重要参数

框架参数

  • n_estimators:最大弱学习器的个数。一般来说n_estimators太小容易欠拟合,数量太多容易过拟合。实际调参时n_estimators与learning_rate一起考虑。
  • learning_rate:学习率,每个弱学习器的权重缩减系数v,也称作步长,取值在0到1之间。v越小,弱学习器迭代次数越多。
  • subsample:子采样率,取值在0到1之间。若取值为1,则使用全部样本。如果取值小于1,则只有部分样本会做XGBoost拟合,可以减少方差,防止过拟合;但同时会增大样本拟合的偏差,因此取值不能太低。

弱学习器参数

  • max_features:决策树划分时考虑的最大特征个数,默认全部考虑。若特征过多可以取部分特征以加快生成时间。
  • colsample_bytree:构建树时的列抽样比例。
  • colsample_bylevel:决策树每层分裂时的列抽样比例。

2.3 XGBoost的优势

  • XGBoost 在损失函数里加入了正则项,用于控制模型的复杂度。从方差和偏差权衡的角度来讲,正则项降低了模型的方差,使训练得出的模型更加简单,能防止过拟合
  • XGBoost 除了决策树外,还支持线性分类器作为弱分类器,此时XGBoost 相当于包含了L1 和L2 正则项的Logistic 回归(分类问题)或者线性回归(回归问题)。
  • XGBoost 借鉴了随机森林的做法,支持特征抽样,在训练弱学习器时,只使用抽样出来的部分特征。这样不仅能降低过拟合,还能减少计算
  • XGBoost 支持并行。但是XGBoost 的并行不是指能够并行地训练决策树,XGBoost 也是训练完一棵决策树再训练下一棵决策树的。XGBoost 是在处理特征的层面上实现并行的。我们知道,训练决策树最耗时的一步就是对各个特征的值进行排序(为了确定最佳分割点)并计算信息增益,XGBoost 对于各个特征的信息增益计算就可以在多线程中进行。

2.4 其他

  • 特征重要性排序:与随机森林类似,基于决策树的XGBoost模型也可以给出特征重要性的排序。其原理与随机森林类似,可参见随机森林专题研究
  • 模型评价:同样可参见随机森林专题研究

3、XGBoost智能选股

%E6%B5%81%E7%A8%8B
$$图4:XGBoost智能选股策略$$
如图4所示,XGBoost的策略构建包含下列步骤:

  • 获取数据 :A股所有股票。
  • 特征和标签提取 :计算18个因子作为样本特征;计算未来5日的个股收益作为样本的标签。
  • 特征预处理 :进行缺失值处理。
  • 模型训练与预测 :使用XGBoost模型进行训练和预测。
  • 策略回测 :利用2010到2017年数据进行训练,预测2017到2019年的股票表现。每日买入预测排名最靠前的5只股票,至少持有五日,同时淘汰排名靠后的股票。具体而言,预测排名越靠前,分配到的资金越多且最大资金占用比例不超过20%;初始5日平均分配资金,之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)。
  • 模型评价 :查看模型回测结果,并与随机森林进行对比。

回测结果如下:


$$图5:XGBoost回测结果$$

对比随机森林在同一时段的回测结果:


$$图6:随机森林回测结果$$
XGBoost与随机森林相比,明显的优势在于回测速度很快,这和其并行处理特征的特点相关。从回测结果来看,XGBoost策略不及随机森林,收益率比随机森林低10%,且最大回撤稍稍高出随机森林2%。当然,经过进一步调参,相信XGBoost的效果会有比较大的提升。

模型评估如下:
%E8%AE%AD%E7%BB%83%E9%9B%86
$$图7:XGBoost训练集评估$$

%E9%A2%84%E6%B5%8B%E9%9B%86
$$图8:XGBoost预测集评估$$

模型评估的结果也表明随机森林的拟合程度更高一些,但是从误差的角度来看,随机森林和XGBoost的差别不大。

欢迎进一步尝试:

克隆策略

    {"Description":"实验创建于2017/8/26","Summary":"","Graph":{"EdgesInternal":[{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"-215:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data1","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15:data"},{"DestinationInputPortId":"-215:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-222:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-231:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-238:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"-9843:features","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:input_data","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data"},{"DestinationInputPortId":"-231:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-250:instruments","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62:data"},{"DestinationInputPortId":"-9843:training_ds","SourceOutputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84:data"},{"DestinationInputPortId":"-9843:predict_ds","SourceOutputPortId":"-86:data"},{"DestinationInputPortId":"-222:input_data","SourceOutputPortId":"-215:data"},{"DestinationInputPortId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53:data2","SourceOutputPortId":"-222:data"},{"DestinationInputPortId":"-238:input_data","SourceOutputPortId":"-231:data"},{"DestinationInputPortId":"-86:input_data","SourceOutputPortId":"-238:data"},{"DestinationInputPortId":"-250:options_data","SourceOutputPortId":"-9843:predictions"}],"ModuleNodes":[{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2010-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"2017-01-01","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-8","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":1,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","ModuleId":"BigQuantSpace.advanced_auto_labeler.advanced_auto_labeler-v2","ModuleParameters":[{"Name":"label_expr","Value":"# #号开始的表示注释\n# 0. 每行一个,顺序执行,从第二个开始,可以使用label字段\n# 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html\n# 添加benchmark_前缀,可使用对应的benchmark数据\n# 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_\n\n# 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)\nshift(close, -5) / shift(open, -1)\n\n# 极值处理:用1%和99%分位的值做clip\nclip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))\n\n# 将分数映射到分类,这里使用20个分类\nall_wbins(label, 20)\n\n# 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)\nwhere(shift(high, -1) == shift(low, -1), NaN, label)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na_label","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"cast_label_int","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-15","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":2,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","ModuleId":"BigQuantSpace.input_features.input_features-v1","ModuleParameters":[{"Name":"features","Value":"(close_0-mean(close_0,12))/mean(close_0,12)*100\nrank(std(amount_0,15))\nrank_avg_amount_0/rank_avg_amount_8\nts_argmin(low_0,20)\nrank_return_30\n(low_1-close_0)/close_0\nta_bbands_lowerband_14_0\nmean(mf_net_pct_s_0,4)\namount_0/avg_amount_3\nreturn_0/return_5\nreturn_1/return_5\nrank_avg_amount_7/rank_avg_amount_10\nta_sma_10_0/close_0\nsqrt(high_0*low_0)-amount_0/volume_0*adjust_factor_0\navg_turn_15/(turn_0+1e-5)\nreturn_10\nmf_net_pct_s_0\n(close_0-open_0)/close_1","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features_ds","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-24","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":3,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","ModuleId":"BigQuantSpace.join.join-v3","ModuleParameters":[{"Name":"on","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"how","Value":"inner","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"sort","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data1","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"data2","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-53","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":7,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","ModuleId":"BigQuantSpace.instruments.instruments-v2","ModuleParameters":[{"Name":"start_date","Value":"2017-01-01","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"end_date","Value":"2019-04-17","ValueType":"Literal","LinkedGlobalParameter":"交易日期"},{"Name":"market","Value":"CN_STOCK_A","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_list","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_count","Value":"0","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"rolling_conf","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-62","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":9,"IsPartOfPartialRun":null,"Comment":"预测数据,用于回测和模拟","CommentCollapsed":false},{"Id":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84"}],"OutputPortsInternal":[{"Name":"data","NodeId":"287d2cb0-f53c-4101-bdf8-104b137c8601-84","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":13,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-86","ModuleId":"BigQuantSpace.dropnan.dropnan-v1","ModuleParameters":[],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-86"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-86","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":14,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-215","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-215"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-215"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-215","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":15,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-222","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-222"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-222"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-222","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":16,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-231","ModuleId":"BigQuantSpace.general_feature_extractor.general_feature_extractor-v7","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_start_days","Value":0,"ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-231"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-231"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-231","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":17,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-238","ModuleId":"BigQuantSpace.derived_feature_extractor.derived_feature_extractor-v3","ModuleParameters":[{"Name":"date_col","Value":"date","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"instrument_col","Value":"instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"drop_na","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"remove_extra_columns","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"user_functions","Value":"","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"input_data","NodeId":"-238"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-238"}],"OutputPortsInternal":[{"Name":"data","NodeId":"-238","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":18,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-250","ModuleId":"BigQuantSpace.trade.trade-v4","ModuleParameters":[{"Name":"start_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"end_date","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"handle_data","Value":"# 回测引擎:每日数据处理函数,每天执行一次\ndef bigquant_run(context, data):\n # 按日期过滤得到今日的预测数据\n ranker_prediction = context.ranker_prediction[\n context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]\n \n ranker_prediction = ranker_prediction.sort_values('pred_label', ascending=False)\n \n # 1. 资金分配\n # 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金\n # 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)\n is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)\n cash_avg = context.portfolio.portfolio_value / context.options['hold_days']\n cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)\n cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)\n positions = {e.symbol: p.amount * p.last_sale_price\n for e, p in context.portfolio.positions.items()}\n\n # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰\n if not is_staging and cash_for_sell > 0:\n equities = {e.symbol: e for e, p in context.portfolio.positions.items()}\n instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(\n lambda x: x in equities)])))\n\n for instrument in instruments:\n context.order_target(context.symbol(instrument), 0)\n cash_for_sell -= positions[instrument]\n if cash_for_sell <= 0:\n break\n\n # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票\n buy_cash_weights = context.stock_weights\n buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])\n max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument\n for i, instrument in enumerate(buy_instruments):\n cash = cash_for_buy * buy_cash_weights[i]\n if cash > max_cash_per_instrument - positions.get(instrument, 0):\n # 确保股票持仓量不会超过每次股票最大的占用资金量\n cash = max_cash_per_instrument - positions.get(instrument, 0)\n if cash > 0:\n context.order_value(context.symbol(instrument), cash)\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"prepare","Value":"# 回测引擎:准备数据,只执行一次\ndef bigquant_run(context):\n pass\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"initialize","Value":"# 回测引擎:初始化函数,只执行一次\ndef bigquant_run(context):\n # 加载预测数据\n context.ranker_prediction = context.options['data'].read_df()\n\n # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数\n context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))\n # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)\n # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只\n stock_count = 5\n # 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]\n context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])\n # 设置每只股票占用的最大资金比例\n context.max_cash_per_instrument = 0.2\n context.options['hold_days'] = 5\n","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"before_trading_start","Value":"","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"volume_limit","Value":0.025,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_buy","Value":"open","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"order_price_field_sell","Value":"close","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"capital_base","Value":1000000,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"auto_cancel_non_tradable_orders","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"data_frequency","Value":"daily","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"price_type","Value":"后复权","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"product_type","Value":"股票","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"plot_charts","Value":"True","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"backtest_only","Value":"False","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"benchmark","Value":"000300.SHA","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"instruments","NodeId":"-250"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"options_data","NodeId":"-250"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"history_ds","NodeId":"-250"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"benchmark_ds","NodeId":"-250"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"trading_calendar","NodeId":"-250"}],"OutputPortsInternal":[{"Name":"raw_perf","NodeId":"-250","OutputType":null}],"UsePreviousResults":false,"moduleIdForCode":19,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true},{"Id":"-9843","ModuleId":"BigQuantSpace.gradient_boosting_regressor.gradient_boosting_regressor-v1","ModuleParameters":[{"Name":"loss","Value":"ls","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"learning_rate","Value":0.1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"iterations","Value":"50","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"subsample","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"min_samples_per_leaf","Value":"1","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"max_depth","Value":"3","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"feature_fraction","Value":1,"ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"key_cols","Value":"date,instrument","ValueType":"Literal","LinkedGlobalParameter":null},{"Name":"other_train_parameters","Value":"{}","ValueType":"Literal","LinkedGlobalParameter":null}],"InputPortsInternal":[{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"training_ds","NodeId":"-9843"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"features","NodeId":"-9843"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"model","NodeId":"-9843"},{"DataSourceId":null,"TrainedModelId":null,"TransformModuleId":null,"Name":"predict_ds","NodeId":"-9843"}],"OutputPortsInternal":[{"Name":"output_model","NodeId":"-9843","OutputType":null},{"Name":"predictions","NodeId":"-9843","OutputType":null}],"UsePreviousResults":true,"moduleIdForCode":5,"IsPartOfPartialRun":null,"Comment":"","CommentCollapsed":true}],"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-8' Position='209,64,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-15' Position='68,183,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-24' Position='763,21,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-53' Position='220,368,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-62' Position='1104,30,200,200'/><NodePosition Node='287d2cb0-f53c-4101-bdf8-104b137c8601-84' Position='328,471,200,200'/><NodePosition Node='-86' Position='940,409,200,200'/><NodePosition Node='-215' Position='379,188,200,200'/><NodePosition Node='-222' Position='385,280,200,200'/><NodePosition Node='-231' Position='1078,237,200,200'/><NodePosition Node='-238' Position='1058,311,200,200'/><NodePosition Node='-250' Position='837,703,200,200'/><NodePosition Node='-9843' Position='581,579,200,200'/></NodePositions><NodeGroups /></DataV1>"},"IsDraft":true,"ParentExperimentId":null,"WebService":{"IsWebServiceExperiment":false,"Inputs":[],"Outputs":[],"Parameters":[{"Name":"交易日期","Value":"","ParameterDefinition":{"Name":"交易日期","FriendlyName":"交易日期","DefaultValue":"","ParameterType":"String","HasDefaultValue":true,"IsOptional":true,"ParameterRules":[],"HasRules":false,"MarkupType":0,"CredentialDescriptor":null}}],"WebServiceGroupId":null,"SerializedClientData":"<?xml version='1.0' encoding='utf-16'?><DataV1 xmlns:xsd='http://www.w3.org/2001/XMLSchema' xmlns:xsi='http://www.w3.org/2001/XMLSchema-instance'><Meta /><NodePositions></NodePositions><NodeGroups /></DataV1>"},"DisableNodesUpdate":false,"Category":"user","Tags":[],"IsPartialRun":true}
    In [1]:
    # 本代码由可视化策略环境自动生成 2019年4月24日 18:01
    # 本代码单元只能在可视化模式下编辑。您也可以拷贝代码,粘贴到新建的代码单元或者策略,然后修改。
    
    
    # 回测引擎:每日数据处理函数,每天执行一次
    def m19_handle_data_bigquant_run(context, data):
        # 按日期过滤得到今日的预测数据
        ranker_prediction = context.ranker_prediction[
            context.ranker_prediction.date == data.current_dt.strftime('%Y-%m-%d')]
        
        ranker_prediction = ranker_prediction.sort_values('pred_label', ascending=False)
     
        # 1. 资金分配
        # 平均持仓时间是hold_days,每日都将买入股票,每日预期使用 1/hold_days 的资金
        # 实际操作中,会存在一定的买入误差,所以在前hold_days天,等量使用资金;之后,尽量使用剩余资金(这里设置最多用等量的1.5倍)
        is_staging = context.trading_day_index < context.options['hold_days'] # 是否在建仓期间(前 hold_days 天)
        cash_avg = context.portfolio.portfolio_value / context.options['hold_days']
        cash_for_buy = min(context.portfolio.cash, (1 if is_staging else 1.5) * cash_avg)
        cash_for_sell = cash_avg - (context.portfolio.cash - cash_for_buy)
        positions = {e.symbol: p.amount * p.last_sale_price
                     for e, p in context.portfolio.positions.items()}
    
        # 2. 生成卖出订单:hold_days天之后才开始卖出;对持仓的股票,按机器学习算法预测的排序末位淘汰
        if not is_staging and cash_for_sell > 0:
            equities = {e.symbol: e for e, p in context.portfolio.positions.items()}
            instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                    lambda x: x in equities)])))
    
            for instrument in instruments:
                context.order_target(context.symbol(instrument), 0)
                cash_for_sell -= positions[instrument]
                if cash_for_sell <= 0:
                    break
    
        # 3. 生成买入订单:按机器学习算法预测的排序,买入前面的stock_count只股票
        buy_cash_weights = context.stock_weights
        buy_instruments = list(ranker_prediction.instrument[:len(buy_cash_weights)])
        max_cash_per_instrument = context.portfolio.portfolio_value * context.max_cash_per_instrument
        for i, instrument in enumerate(buy_instruments):
            cash = cash_for_buy * buy_cash_weights[i]
            if cash > max_cash_per_instrument - positions.get(instrument, 0):
                # 确保股票持仓量不会超过每次股票最大的占用资金量
                cash = max_cash_per_instrument - positions.get(instrument, 0)
            if cash > 0:
                context.order_value(context.symbol(instrument), cash)
    
    # 回测引擎:准备数据,只执行一次
    def m19_prepare_bigquant_run(context):
        pass
    
    # 回测引擎:初始化函数,只执行一次
    def m19_initialize_bigquant_run(context):
        # 加载预测数据
        context.ranker_prediction = context.options['data'].read_df()
    
        # 系统已经设置了默认的交易手续费和滑点,要修改手续费可使用如下函数
        context.set_commission(PerOrder(buy_cost=0.0003, sell_cost=0.0013, min_cost=5))
        # 预测数据,通过options传入进来,使用 read_df 函数,加载到内存 (DataFrame)
        # 设置买入的股票数量,这里买入预测股票列表排名靠前的5只
        stock_count = 5
        # 每只的股票的权重,如下的权重分配会使得靠前的股票分配多一点的资金,[0.339160, 0.213986, 0.169580, ..]
        context.stock_weights = T.norm([1 / math.log(i + 2) for i in range(0, stock_count)])
        # 设置每只股票占用的最大资金比例
        context.max_cash_per_instrument = 0.2
        context.options['hold_days'] = 5
    
    
    m1 = M.instruments.v2(
        start_date='2010-01-01',
        end_date='2017-01-01',
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m2 = M.advanced_auto_labeler.v2(
        instruments=m1.data,
        label_expr="""# #号开始的表示注释
    # 0. 每行一个,顺序执行,从第二个开始,可以使用label字段
    # 1. 可用数据字段见 https://bigquant.com/docs/develop/datasource/deprecated/history_data.html
    #   添加benchmark_前缀,可使用对应的benchmark数据
    # 2. 可用操作符和函数见 `表达式引擎 <https://bigquant.com/docs/develop/bigexpr/usage.html>`_
    
    # 计算收益:5日收盘价(作为卖出价格)除以明日开盘价(作为买入价格)
    shift(close, -5) / shift(open, -1)
    
    # 极值处理:用1%和99%分位的值做clip
    clip(label, all_quantile(label, 0.01), all_quantile(label, 0.99))
    
    # 将分数映射到分类,这里使用20个分类
    all_wbins(label, 20)
    
    # 过滤掉一字涨停的情况 (设置label为NaN,在后续处理和训练中会忽略NaN的label)
    where(shift(high, -1) == shift(low, -1), NaN, label)
    """,
        start_date='',
        end_date='',
        benchmark='000300.SHA',
        drop_na_label=True,
        cast_label_int=True
    )
    
    m3 = M.input_features.v1(
        features="""(close_0-mean(close_0,12))/mean(close_0,12)*100
    rank(std(amount_0,15))
    rank_avg_amount_0/rank_avg_amount_8
    ts_argmin(low_0,20)
    rank_return_30
    (low_1-close_0)/close_0
    ta_bbands_lowerband_14_0
    mean(mf_net_pct_s_0,4)
    amount_0/avg_amount_3
    return_0/return_5
    return_1/return_5
    rank_avg_amount_7/rank_avg_amount_10
    ta_sma_10_0/close_0
    sqrt(high_0*low_0)-amount_0/volume_0*adjust_factor_0
    avg_turn_15/(turn_0+1e-5)
    return_10
    mf_net_pct_s_0
    (close_0-open_0)/close_1"""
    )
    
    m15 = M.general_feature_extractor.v7(
        instruments=m1.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=0
    )
    
    m16 = M.derived_feature_extractor.v3(
        input_data=m15.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False
    )
    
    m7 = M.join.v3(
        data1=m2.data,
        data2=m16.data,
        on='date,instrument',
        how='inner',
        sort=False
    )
    
    m13 = M.dropnan.v1(
        input_data=m7.data
    )
    
    m9 = M.instruments.v2(
        start_date=T.live_run_param('trading_date', '2017-01-01'),
        end_date=T.live_run_param('trading_date', '2019-04-17'),
        market='CN_STOCK_A',
        instrument_list='',
        max_count=0
    )
    
    m17 = M.general_feature_extractor.v7(
        instruments=m9.data,
        features=m3.data,
        start_date='',
        end_date='',
        before_start_days=0
    )
    
    m18 = M.derived_feature_extractor.v3(
        input_data=m17.data,
        features=m3.data,
        date_col='date',
        instrument_col='instrument',
        drop_na=False,
        remove_extra_columns=False
    )
    
    m14 = M.dropnan.v1(
        input_data=m18.data
    )
    
    m5 = M.gradient_boosting_regressor.v1(
        training_ds=m13.data,
        features=m3.data,
        predict_ds=m14.data,
        loss='ls',
        learning_rate=0.1,
        iterations=50,
        subsample=1,
        min_samples_per_leaf=1,
        max_depth=3,
        feature_fraction=1,
        key_cols='date,instrument',
        other_train_parameters={}
    )
    
    m19 = M.trade.v4(
        instruments=m9.data,
        options_data=m5.predictions,
        start_date='',
        end_date='',
        handle_data=m19_handle_data_bigquant_run,
        prepare=m19_prepare_bigquant_run,
        initialize=m19_initialize_bigquant_run,
        volume_limit=0.025,
        order_price_field_buy='open',
        order_price_field_sell='close',
        capital_base=1000000,
        auto_cancel_non_tradable_orders=True,
        data_frequency='daily',
        price_type='后复权',
        product_type='股票',
        plot_charts=True,
        backtest_only=False,
        benchmark='000300.SHA'
    )
    
    • 收益率55.3%
    • 年化收益率22.04%
    • 基准收益率23.48%
    • 阿尔法0.16
    • 贝塔0.6
    • 夏普比率0.74
    • 胜率0.53
    • 盈亏比1.08
    • 收益波动率28.38%
    • 信息比率0.03
    • 最大回撤25.64%
    bigcharts-data-start/{"__type":"tabs","__id":"bigchart-93d9818500704e9b9a3dee6e927e8ae8"}/bigcharts-data-end

    参考文献


    【专题研究】基于SVM支持向量机模型的选股策略
    深度学习前沿 | 利用GAN预测股价走势
    (Lyon) #4

    克隆策略后再跑一遍得出的不是这个结果,是个负的收益率


    (mumu) #5

    你好,你的stock_weight设置错误了: 应该使用sum()而不是norm()
    stock_weight = [ 1.0 / np.log( i + 2 ) for i in range( stock_count ) ]
    stock_weight /= np.sum( stock_weight )
    print( stock_weight )
    #[0.33916021 0.21398626 0.1695801 0.14606835 0.13120508]