复制链接

克隆策略

策略简介¶

因子：样例因子（7个）

因子是否标准化：是

标注：未来5日收益(不做离散化)

算法：DNN

类型：回归问题

训练集：10-15年

测试集：16-19年

选股依据：根据预测值降序排序买入

持股数：30

持仓天数：5

模型结构

输入层 7 - 因子数量

全连接层 256 激活函数为relu

dropout 0.1

全连接层 128 激活函数为relu

全连接层 1 激活函数为linear - 预测输出

In [1]:

# 本代码由可视化策略环境自动生成 2023年2月21日 20:08
# 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。


# 用户的自定义层需要写到字典中，比如
# {
#   "MyLayer": MyLayer
# }
m5_custom_objects_bigquant_run = {
    
}

# Python 代码入口函数，input_1/2/3 对应三个输入端，data_1/2/3 对应三个输出端
def m24_run_bigquant_run(input_1, input_2, input_3):
    # 示例代码如下。在这里编写您的代码
    pred_label = input_1.read_pickle()
    df = input_2.read_df()
    df = pd.DataFrame({'pred_label':pred_label[:,0], 'instrument':df.instrument, 'date':df.date})
    df.sort_values(['date','pred_label'],inplace=True, ascending=[True,False])
    return Outputs(data_1=DataSource.write_df(df), data_2=None, data_3=None)

# 后处理函数，可选。输入是主函数的输出，可以在这里对数据做处理，或者返回更友好的outputs数据格式。此函数输出不会被缓存。
def m24_post_run_bigquant_run(outputs):
    return outputs

# 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 = 1
    # 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 = 1
    context.options['hold_days'] = 3

# 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')]

    # 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.perf_tracker.position_tracker.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.perf_tracker.position_tracker.positions.items()}
        instruments = list(reversed(list(ranker_prediction.instrument[ranker_prediction.instrument.apply(
                lambda x: x in equities and not context.has_unfinished_sell_order(equities[x]))])))
        # print('rank order for sell %s' % instruments)
        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


m1 = M.instruments.v2(
    start_date='2021-01-01',
    end_date=T.live_run_param('trading_date', '2023-1-31'),
    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/data_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/big_expr.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)-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))

# 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=False
)

m13 = M.standardlize.v8(
    input_1=m2.data,
    columns_input='label',
    m_cached=False
)

m3 = M.input_features.v1(
    features="""close_0/mean(close_0,5)
close_0/mean(close_0,10)
close_0/mean(close_0,20)
close_0/open_0
open_0/mean(close_0,5)
open_0/mean(close_0,10)
open_0/mean(close_0,20)""",
    m_cached=False
)

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=True,
    remove_extra_columns=False
)

m14 = M.standardlize.v8(
    input_1=m16.data,
    input_2=m3.data,
    columns_input='[]'
)

m7 = M.join.v3(
    data1=m13.data,
    data2=m14.data,
    on='date,instrument',
    how='inner',
    sort=False
)

m26 = M.dl_convert_to_bin.v2(
    input_data=m7.data,
    features=m3.data,
    window_size=1,
    feature_clip=5,
    flatten=True,
    window_along_col='instrument'
)

m9 = M.instruments.v2(
    start_date=T.live_run_param('trading_date', '2020-01-01'),
    end_date=T.live_run_param('trading_date', '2022-04-20'),
    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=True,
    remove_extra_columns=False
)

m25 = M.standardlize.v8(
    input_1=m18.data,
    input_2=m3.data,
    columns_input='[]'
)

m27 = M.dl_convert_to_bin.v2(
    input_data=m25.data,
    features=m3.data,
    window_size=1,
    feature_clip=5,
    flatten=True,
    window_along_col='instrument'
)

m6 = M.dl_layer_input.v1(
    shape='7',
    batch_shape='',
    dtype='float32',
    sparse=False,
    name=''
)

m8 = M.dl_layer_dense.v1(
    inputs=m6.data,
    units=256,
    activation='relu',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='Zeros',
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    bias_regularizer='None',
    bias_regularizer_l1=0,
    bias_regularizer_l2=0,
    activity_regularizer='None',
    activity_regularizer_l1=0,
    activity_regularizer_l2=0,
    kernel_constraint='None',
    bias_constraint='None',
    name=''
)

m21 = M.dl_layer_dropout.v1(
    inputs=m8.data,
    rate=0.1,
    noise_shape='',
    name=''
)

m20 = M.dl_layer_dense.v1(
    inputs=m21.data,
    units=128,
    activation='relu',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='Zeros',
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    bias_regularizer='None',
    bias_regularizer_l1=0,
    bias_regularizer_l2=0,
    activity_regularizer='None',
    activity_regularizer_l1=0,
    activity_regularizer_l2=0,
    kernel_constraint='None',
    bias_constraint='None',
    name=''
)

m22 = M.dl_layer_dropout.v1(
    inputs=m20.data,
    rate=0.1,
    noise_shape='',
    name=''
)

m23 = M.dl_layer_dense.v1(
    inputs=m22.data,
    units=1,
    activation='linear',
    use_bias=True,
    kernel_initializer='glorot_uniform',
    bias_initializer='Zeros',
    kernel_regularizer='None',
    kernel_regularizer_l1=0,
    kernel_regularizer_l2=0,
    bias_regularizer='None',
    bias_regularizer_l1=0,
    bias_regularizer_l2=0,
    activity_regularizer='None',
    activity_regularizer_l1=0,
    activity_regularizer_l2=0,
    kernel_constraint='None',
    bias_constraint='None',
    name=''
)

m4 = M.dl_model_init.v1(
    inputs=m6.data,
    outputs=m23.data
)

m5 = M.dl_model_train.v1(
    input_model=m4.data,
    training_data=m26.data,
    optimizer='Adamax',
    loss='mean_squared_error',
    metrics='mse',
    batch_size=1024,
    epochs=120,
    custom_objects=m5_custom_objects_bigquant_run,
    n_gpus=0,
    verbose='2:每个epoch输出一行记录'
)

m11 = M.dl_model_predict.v1(
    trained_model=m5.data,
    input_data=m27.data,
    batch_size=1024,
    n_gpus=0,
    verbose='2:每个epoch输出一行记录'
)

m24 = M.cached.v3(
    input_1=m11.data,
    input_2=m18.data,
    run=m24_run_bigquant_run,
    post_run=m24_post_run_bigquant_run,
    input_ports='',
    params='{}',
    output_ports=''
)

m19 = M.trade.v4(
    instruments=m9.data,
    options_data=m24.data_1,
    start_date='2022-01-01',
    end_date='2023-1-31',
    initialize=m19_initialize_bigquant_run,
    handle_data=m19_handle_data_bigquant_run,
    prepare=m19_prepare_bigquant_run,
    volume_limit=0.025,
    order_price_field_buy='open',
    order_price_field_sell='close',
    capital_base=10000,
    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'
)

[2023-02-21 13:29:37.059996] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-02-21 13:29:37.130274] INFO: moduleinvoker: instruments.v2 运行完成[0.070278s].

[2023-02-21 13:29:37.139483] INFO: moduleinvoker: advanced_auto_labeler.v2 开始运行..

[2023-02-21 13:29:39.217973] INFO: 自动标注(股票): 加载历史数据: 2313581 行

[2023-02-21 13:29:39.219423] INFO: 自动标注(股票): 开始标注 ..

[2023-02-21 13:29:41.476517] INFO: moduleinvoker: advanced_auto_labeler.v2 运行完成[4.337025s].

[2023-02-21 13:29:41.486357] INFO: moduleinvoker: standardlize.v8 开始运行..

[2023-02-21 13:29:57.305131] INFO: moduleinvoker: standardlize.v8 运行完成[15.81876s].

[2023-02-21 13:29:57.312561] INFO: moduleinvoker: input_features.v1 开始运行..

[2023-02-21 13:29:57.400013] INFO: moduleinvoker: input_features.v1 运行完成[0.087413s].

[2023-02-21 13:29:57.419697] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-02-21 13:29:58.316924] INFO: 基础特征抽取: 年份 2021, 特征行数=1061527

[2023-02-21 13:29:59.215177] INFO: 基础特征抽取: 年份 2022, 特征行数=1171038

[2023-02-21 13:29:59.322110] INFO: 基础特征抽取: 年份 2023, 特征行数=81016

[2023-02-21 13:29:59.398369] INFO: 基础特征抽取: 总行数: 2313581

[2023-02-21 13:29:59.402650] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[1.982952s].

[2023-02-21 13:29:59.411850] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-02-21 13:30:03.249052] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,5), 1.236s

[2023-02-21 13:30:04.509160] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,10), 1.259s

[2023-02-21 13:30:05.743280] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,20), 1.233s

[2023-02-21 13:30:05.748236] INFO: derived_feature_extractor: 提取完成 close_0/open_0, 0.004s

[2023-02-21 13:30:06.983048] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,5), 1.234s

[2023-02-21 13:30:08.392894] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,10), 1.408s

[2023-02-21 13:30:09.709327] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,20), 1.315s

[2023-02-21 13:30:11.106725] INFO: derived_feature_extractor: /y_2021, 1061527

[2023-02-21 13:30:13.229131] INFO: derived_feature_extractor: /y_2022, 1171038

[2023-02-21 13:30:14.069442] INFO: derived_feature_extractor: /y_2023, 81016

[2023-02-21 13:30:14.255166] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[14.843276s].

[2023-02-21 13:30:14.263935] INFO: moduleinvoker: standardlize.v8 开始运行..

[2023-02-21 13:30:38.470370] INFO: moduleinvoker: standardlize.v8 运行完成[24.206429s].

[2023-02-21 13:30:38.480765] INFO: moduleinvoker: join.v3 开始运行..

[2023-02-21 13:30:46.347538] INFO: join: /data, 行数=2186225/2216123, 耗时=4.807286s

[2023-02-21 13:30:46.422187] INFO: join: 最终行数: 2186225

[2023-02-21 13:30:46.441046] INFO: moduleinvoker: join.v3 运行完成[7.960277s].

[2023-02-21 13:30:46.465798] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2023-02-21 13:30:49.843732] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[3.377901s].

[2023-02-21 13:30:49.849646] INFO: moduleinvoker: instruments.v2 开始运行..

[2023-02-21 13:30:49.925256] INFO: moduleinvoker: instruments.v2 运行完成[0.075594s].

[2023-02-21 13:30:49.939308] INFO: moduleinvoker: general_feature_extractor.v7 开始运行..

[2023-02-21 13:30:50.763799] INFO: 基础特征抽取: 年份 2020, 特征行数=945961

[2023-02-21 13:30:51.626016] INFO: 基础特征抽取: 年份 2021, 特征行数=1061527

[2023-02-21 13:30:52.010504] INFO: 基础特征抽取: 年份 2022, 特征行数=330563

[2023-02-21 13:30:52.115815] INFO: 基础特征抽取: 总行数: 2338051

[2023-02-21 13:30:52.120798] INFO: moduleinvoker: general_feature_extractor.v7 运行完成[2.181493s].

[2023-02-21 13:30:52.127950] INFO: moduleinvoker: derived_feature_extractor.v3 开始运行..

[2023-02-21 13:30:55.958290] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,5), 1.216s

[2023-02-21 13:30:57.153547] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,10), 1.194s

[2023-02-21 13:30:58.370874] INFO: derived_feature_extractor: 提取完成 close_0/mean(close_0,20), 1.216s

[2023-02-21 13:30:58.375696] INFO: derived_feature_extractor: 提取完成 close_0/open_0, 0.003s

[2023-02-21 13:30:59.593477] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,5), 1.217s

[2023-02-21 13:31:00.882687] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,10), 1.288s

[2023-02-21 13:31:02.155659] INFO: derived_feature_extractor: 提取完成 open_0/mean(close_0,20), 1.272s

[2023-02-21 13:31:03.548027] INFO: derived_feature_extractor: /y_2020, 945961

[2023-02-21 13:31:05.146679] INFO: derived_feature_extractor: /y_2021, 1061527

[2023-02-21 13:31:06.134085] INFO: derived_feature_extractor: /y_2022, 330563

[2023-02-21 13:31:06.546076] INFO: moduleinvoker: derived_feature_extractor.v3 运行完成[14.418117s].

[2023-02-21 13:31:06.551308] INFO: moduleinvoker: standardlize.v8 开始运行..

[2023-02-21 13:31:30.133068] INFO: moduleinvoker: standardlize.v8 运行完成[23.581745s].

[2023-02-21 13:31:30.146795] INFO: moduleinvoker: dl_convert_to_bin.v2 开始运行..

[2023-02-21 13:31:33.348888] INFO: moduleinvoker: dl_convert_to_bin.v2 运行完成[3.202089s].

[2023-02-21 13:31:36.423448] INFO: moduleinvoker: dl_layer_input.v1 运行完成[3.061699s].

[2023-02-21 13:31:36.471885] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.039745s].

[2023-02-21 13:31:36.483846] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.003403s].

[2023-02-21 13:31:36.497107] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.007315s].

[2023-02-21 13:31:36.504631] INFO: moduleinvoker: dl_layer_dropout.v1 运行完成[0.00242s].

[2023-02-21 13:31:36.517710] INFO: moduleinvoker: dl_layer_dense.v1 运行完成[0.00799s].

[2023-02-21 13:31:36.546572] INFO: moduleinvoker: cached.v3 开始运行..

[2023-02-21 13:31:36.560893] INFO: moduleinvoker: 命中缓存

[2023-02-21 13:31:36.561983] INFO: moduleinvoker: cached.v3 运行完成[0.015423s].

[2023-02-21 13:31:36.564456] INFO: moduleinvoker: dl_model_init.v1 运行完成[0.040324s].

[2023-02-21 13:31:36.576039] INFO: moduleinvoker: dl_model_train.v1 开始运行..

[2023-02-21 13:31:36.817883] INFO: dl_model_train: 准备训练，训练样本个数：2186225，迭代次数：120

[2023-02-21 15:56:21.351163] INFO: dl_model_train: 训练结束，耗时：8684.53s

[2023-02-21 15:56:21.943240] INFO: moduleinvoker: dl_model_train.v1 运行完成[8685.367175s].

[2023-02-21 15:56:21.954293] INFO: moduleinvoker: dl_model_predict.v1 开始运行..

[2023-02-21 15:56:48.051684] INFO: moduleinvoker: dl_model_predict.v1 运行完成[26.097384s].

[2023-02-21 15:56:48.244216] INFO: moduleinvoker: cached.v3 开始运行..

[2023-02-21 15:57:37.660756] INFO: moduleinvoker: cached.v3 运行完成[49.416544s].

[2023-02-21 15:58:02.252420] INFO: moduleinvoker: backtest.v8 开始运行..

[2023-02-21 15:58:02.344215] INFO: backtest: biglearning backtest:V8.6.3

[2023-02-21 15:58:02.345814] INFO: backtest: product_type:stock by specified

[2023-02-21 15:58:02.854256] INFO: moduleinvoker: cached.v2 开始运行..

[2023-02-21 15:59:08.746043] INFO: backtest: 读取股票行情完成:2551915

[2023-02-21 15:59:25.846799] INFO: moduleinvoker: cached.v2 运行完成[82.992518s].

[2023-02-21 16:00:46.851324] INFO: backtest: algo history_data=DataSource(04fcdc6a848c453b8b64249dc5daeb52T)

[2023-02-21 16:00:46.853106] INFO: algo: TradingAlgorithm V1.8.9

[2023-02-21 16:01:16.251421] INFO: algo: trading transform...

[2023-02-21 16:01:28.654370] WARNING: Performance: maybe_close_position no price for asset:Equity(285 [600145.SHA]), field:price, dt:2022-04-28 15:00:00+00:00

[2023-02-21 16:01:42.944863] INFO: Performance: Simulated 258 trading days out of 258.

[2023-02-21 16:01:42.946927] INFO: Performance: first open: 2022-01-04 09:30:00+00:00

[2023-02-21 16:01:42.948618] INFO: Performance: last close: 2023-01-31 15:00:00+00:00

[2023-02-21 16:02:00.142731] INFO: moduleinvoker: backtest.v8 运行完成[237.890307s].

[2023-02-21 16:02:00.144849] INFO: moduleinvoker: trade.v4 运行完成[262.387545s].

Epoch 1/120
2135/2135 - 54s - loss: 0.9884 - mse: 0.9884
Epoch 2/120
2135/2135 - 55s - loss: 0.9868 - mse: 0.9868
Epoch 3/120
2135/2135 - 60s - loss: 0.9867 - mse: 0.9867
Epoch 4/120
2135/2135 - 60s - loss: 0.9866 - mse: 0.9866
Epoch 5/120
2135/2135 - 60s - loss: 0.9865 - mse: 0.9865
Epoch 6/120
2135/2135 - 61s - loss: 0.9865 - mse: 0.9865
Epoch 7/120
2135/2135 - 61s - loss: 0.9865 - mse: 0.9865
Epoch 8/120
2135/2135 - 60s - loss: 0.9864 - mse: 0.9864
Epoch 9/120
2135/2135 - 60s - loss: 0.9864 - mse: 0.9864
Epoch 10/120
2135/2135 - 60s - loss: 0.9864 - mse: 0.9864
Epoch 11/120
2135/2135 - 60s - loss: 0.9863 - mse: 0.9863
Epoch 12/120
2135/2135 - 60s - loss: 0.9863 - mse: 0.9863
Epoch 13/120
2135/2135 - 60s - loss: 0.9863 - mse: 0.9863
Epoch 14/120
2135/2135 - 60s - loss: 0.9863 - mse: 0.9863
Epoch 15/120
2135/2135 - 60s - loss: 0.9863 - mse: 0.9863
Epoch 16/120
2135/2135 - 60s - loss: 0.9863 - mse: 0.9863
Epoch 17/120
2135/2135 - 60s - loss: 0.9862 - mse: 0.9862
Epoch 18/120
2135/2135 - 60s - loss: 0.9862 - mse: 0.9862
Epoch 19/120
2135/2135 - 59s - loss: 0.9862 - mse: 0.9862
Epoch 20/120
2135/2135 - 60s - loss: 0.9862 - mse: 0.9862
Epoch 21/120
2135/2135 - 58s - loss: 0.9861 - mse: 0.9861
Epoch 22/120
2135/2135 - 61s - loss: 0.9861 - mse: 0.9861
Epoch 23/120
2135/2135 - 62s - loss: 0.9861 - mse: 0.9861
Epoch 24/120
2135/2135 - 62s - loss: 0.9860 - mse: 0.9860
Epoch 25/120
2135/2135 - 62s - loss: 0.9860 - mse: 0.9860
Epoch 26/120
2135/2135 - 62s - loss: 0.9860 - mse: 0.9860
Epoch 27/120
2135/2135 - 61s - loss: 0.9859 - mse: 0.9859
Epoch 28/120
2135/2135 - 60s - loss: 0.9859 - mse: 0.9859
Epoch 29/120
2135/2135 - 60s - loss: 0.9859 - mse: 0.9859
Epoch 30/120
2135/2135 - 61s - loss: 0.9859 - mse: 0.9859
Epoch 31/120
2135/2135 - 59s - loss: 0.9859 - mse: 0.9859
Epoch 32/120
2135/2135 - 83s - loss: 0.9859 - mse: 0.9859
Epoch 33/120
2135/2135 - 106s - loss: 0.9858 - mse: 0.9858
Epoch 34/120
2135/2135 - 106s - loss: 0.9858 - mse: 0.9858
Epoch 35/120
2135/2135 - 106s - loss: 0.9858 - mse: 0.9858
Epoch 36/120
2135/2135 - 104s - loss: 0.9858 - mse: 0.9858
Epoch 37/120
2135/2135 - 105s - loss: 0.9857 - mse: 0.9857
Epoch 38/120
2135/2135 - 104s - loss: 0.9857 - mse: 0.9857
Epoch 39/120
2135/2135 - 105s - loss: 0.9857 - mse: 0.9857
Epoch 40/120
2135/2135 - 105s - loss: 0.9857 - mse: 0.9857
Epoch 41/120
2135/2135 - 105s - loss: 0.9857 - mse: 0.9857
Epoch 42/120
2135/2135 - 104s - loss: 0.9857 - mse: 0.9857
Epoch 43/120
2135/2135 - 105s - loss: 0.9856 - mse: 0.9856
Epoch 44/120
2135/2135 - 105s - loss: 0.9856 - mse: 0.9856
Epoch 45/120
2135/2135 - 105s - loss: 0.9856 - mse: 0.9856
Epoch 46/120
2135/2135 - 104s - loss: 0.9856 - mse: 0.9856
Epoch 47/120
2135/2135 - 105s - loss: 0.9856 - mse: 0.9856
Epoch 48/120
2135/2135 - 104s - loss: 0.9856 - mse: 0.9856
Epoch 49/120
2135/2135 - 104s - loss: 0.9856 - mse: 0.9856
Epoch 50/120
2135/2135 - 105s - loss: 0.9855 - mse: 0.9855
Epoch 51/120
2135/2135 - 105s - loss: 0.9855 - mse: 0.9855
Epoch 52/120
2135/2135 - 104s - loss: 0.9854 - mse: 0.9854
Epoch 53/120
2135/2135 - 104s - loss: 0.9854 - mse: 0.9854
Epoch 54/120
2135/2135 - 104s - loss: 0.9854 - mse: 0.9854
Epoch 55/120
2135/2135 - 104s - loss: 0.9854 - mse: 0.9854
Epoch 56/120
2135/2135 - 106s - loss: 0.9854 - mse: 0.9854
Epoch 57/120
2135/2135 - 105s - loss: 0.9854 - mse: 0.9854
Epoch 58/120
2135/2135 - 105s - loss: 0.9853 - mse: 0.9853
Epoch 59/120
2135/2135 - 105s - loss: 0.9854 - mse: 0.9854
Epoch 60/120
2135/2135 - 105s - loss: 0.9854 - mse: 0.9854
Epoch 61/120
2135/2135 - 105s - loss: 0.9853 - mse: 0.9853
Epoch 62/120
2135/2135 - 105s - loss: 0.9853 - mse: 0.9853
Epoch 63/120
2135/2135 - 106s - loss: 0.9853 - mse: 0.9853
Epoch 64/120
2135/2135 - 105s - loss: 0.9852 - mse: 0.9852
Epoch 65/120
2135/2135 - 73s - loss: 0.9852 - mse: 0.9852
Epoch 66/120
2135/2135 - 60s - loss: 0.9852 - mse: 0.9852
Epoch 67/120
2135/2135 - 55s - loss: 0.9852 - mse: 0.9852
Epoch 68/120
2135/2135 - 52s - loss: 0.9852 - mse: 0.9852
Epoch 69/120
2135/2135 - 52s - loss: 0.9852 - mse: 0.9852
Epoch 70/120
2135/2135 - 52s - loss: 0.9852 - mse: 0.9852
Epoch 71/120
2135/2135 - 52s - loss: 0.9851 - mse: 0.9851
Epoch 72/120
2135/2135 - 52s - loss: 0.9851 - mse: 0.9851
Epoch 73/120
2135/2135 - 52s - loss: 0.9851 - mse: 0.9851
Epoch 74/120
2135/2135 - 52s - loss: 0.9851 - mse: 0.9851
Epoch 75/120
2135/2135 - 52s - loss: 0.9851 - mse: 0.9851
Epoch 76/120
2135/2135 - 52s - loss: 0.9850 - mse: 0.9850
Epoch 77/120
2135/2135 - 52s - loss: 0.9850 - mse: 0.9850
Epoch 78/120
2135/2135 - 53s - loss: 0.9850 - mse: 0.9850
Epoch 79/120
2135/2135 - 52s - loss: 0.9850 - mse: 0.9850
Epoch 80/120
2135/2135 - 53s - loss: 0.9850 - mse: 0.9850
Epoch 81/120
2135/2135 - 53s - loss: 0.9849 - mse: 0.9849
Epoch 82/120
2135/2135 - 53s - loss: 0.9849 - mse: 0.9849
Epoch 83/120
2135/2135 - 52s - loss: 0.9850 - mse: 0.9850
Epoch 84/120
2135/2135 - 52s - loss: 0.9849 - mse: 0.9849
Epoch 85/120
2135/2135 - 52s - loss: 0.9848 - mse: 0.9848
Epoch 86/120
2135/2135 - 52s - loss: 0.9849 - mse: 0.9849
Epoch 87/120
2135/2135 - 52s - loss: 0.9849 - mse: 0.9849
Epoch 88/120
2135/2135 - 53s - loss: 0.9849 - mse: 0.9849
Epoch 89/120
2135/2135 - 52s - loss: 0.9848 - mse: 0.9848
Epoch 90/120
2135/2135 - 59s - loss: 0.9849 - mse: 0.9849
Epoch 91/120
2135/2135 - 61s - loss: 0.9848 - mse: 0.9848
Epoch 92/120
2135/2135 - 61s - loss: 0.9848 - mse: 0.9848
Epoch 93/120
2135/2135 - 61s - loss: 0.9848 - mse: 0.9848
Epoch 94/120
2135/2135 - 60s - loss: 0.9848 - mse: 0.9848
Epoch 95/120
2135/2135 - 61s - loss: 0.9848 - mse: 0.9848
Epoch 96/120
2135/2135 - 61s - loss: 0.9847 - mse: 0.9847
Epoch 97/120
2135/2135 - 61s - loss: 0.9846 - mse: 0.9846
Epoch 98/120
2135/2135 - 61s - loss: 0.9848 - mse: 0.9848
Epoch 99/120
2135/2135 - 61s - loss: 0.9847 - mse: 0.9847
Epoch 100/120
2135/2135 - 60s - loss: 0.9847 - mse: 0.9847
Epoch 101/120
2135/2135 - 61s - loss: 0.9846 - mse: 0.9846
Epoch 102/120
2135/2135 - 61s - loss: 0.9847 - mse: 0.9847
Epoch 103/120
2135/2135 - 60s - loss: 0.9846 - mse: 0.9846
Epoch 104/120
2135/2135 - 60s - loss: 0.9846 - mse: 0.9846
Epoch 105/120
2135/2135 - 61s - loss: 0.9845 - mse: 0.9845
Epoch 106/120
2135/2135 - 60s - loss: 0.9845 - mse: 0.9845
Epoch 107/120
2135/2135 - 61s - loss: 0.9845 - mse: 0.9845
Epoch 108/120
2135/2135 - 61s - loss: 0.9845 - mse: 0.9845
Epoch 109/120
2135/2135 - 61s - loss: 0.9845 - mse: 0.9845
Epoch 110/120
2135/2135 - 60s - loss: 0.9845 - mse: 0.9845
Epoch 111/120
2135/2135 - 61s - loss: 0.9845 - mse: 0.9845
Epoch 112/120
2135/2135 - 61s - loss: 0.9845 - mse: 0.9845
Epoch 113/120
2135/2135 - 61s - loss: 0.9845 - mse: 0.9845
Epoch 114/120
2135/2135 - 62s - loss: 0.9845 - mse: 0.9845
Epoch 115/120
2135/2135 - 61s - loss: 0.9844 - mse: 0.9844
Epoch 116/120
2135/2135 - 60s - loss: 0.9844 - mse: 0.9844
Epoch 117/120
2135/2135 - 87s - loss: 0.9844 - mse: 0.9844
Epoch 118/120
2135/2135 - 105s - loss: 0.9843 - mse: 0.9843
Epoch 119/120
2135/2135 - 106s - loss: 0.9844 - mse: 0.9844
Epoch 120/120
2135/2135 - 106s - loss: 0.9844 - mse: 0.9844

2195/2195 - 23s
DataSource(e7b638bccdbe48a1922f3eeaa59fdbf2T)

收益率57.64%
年化收益率55.98%
基准收益率-15.86%
阿尔法0.64
贝塔0.09
夏普比率1.29
胜率0.54
盈亏比1.44
收益波动率37.34%
信息比率0.1
最大回撤16.46%

bigcharts-data-start/{"__type":"tabs","__id":"bigchart-cb2ba0ddd5544412b8933b7266cbf357"}/bigcharts-data-end