如何解决使用 LSTM 进行高频股票预测的不稳定结果
我有几个包含来自纳斯达克的高频数据(限价订单簿)的数据集。
对于对此类数据感兴趣的任何人,我强烈建议您查看 https://github.com/martinobdl/ITCH 以获取 Book Constructor 和一些示例数据(无论如何,您在其他任何地方都无法获得更多)
我想使用 LSTM 网络尝试预测下一个买价和下一个卖价,同时使用一些其他功能,例如订单簿中的数量和数量不平衡。
这是我的火车数据的前五列的样子(来自 AAPL 的数据,数据点之间的间隔为 1):
Bid Ask 1_bid_vol 1_ask_vol 2_bid_vol 2_ask_vol
162.49 162.52 300.0 200.0 500.0 200.0
162.48 162.51 300.0 600.0 800.0 500.0
162.49 162.51 100.0 10.0 1000.0 500.0
162.48 162.52 469.0 600.0 618.0 500.0
除了规范化数据外,我还创建了适合 LSTM 的固定长度序列,如下所示:
def slicing(df,history_size):
data = []
labels = []
tmp_df=np.array(df)
start_index = history_size
for i in range(start_index,len(df)):
indices = range(i-history_size,i)
data.append(tmp_df[indices,:])
labels.append(tmp_df[i,:2])
return np.array(data),np.array(labels)
使输入数据具有 shape = (n_samples,history_size,n_features)
我目前的架构如下:
callback = tf.keras.callbacks.EarlyStopping(monitor='val_loss',patience=5)
LSTM = tf.keras.models.Sequential([
tf.keras.layers.LSTM(128,input_shape=
(X_train.shape[1],X_train.shape[2]),activation='relu',return_sequences=True),tf.keras.layers.LSTM(62,input_shape=(X_train.shape[1],activation='relu'),tf.keras.layers.Dropout(0.2),tf.keras.layers.Dense(2)
])
opt = tf.keras.optimizers.Adam(learning_rate=0.001)
LSTM.compile(optimizer=opt,loss='mse')
LSTM.fit(x=X_train,y=y_train,epochs=50,validation_data=(X_val,y_val),callbacks=[callback])
这些是我在使用 14k 数据点进行训练的验证集上得到的结果(我会让你们想象一下它在测试集上的样子):
如您所见,该模型在验证集上的起步很好,而不是在此过程中基本上开始预测随机异常值/峰值。
请注意,即使在更改超参数、模型架构甚至更改数据(例如使用其他股票)并使用较小的时间窗口后,该结果仍会始终出现,以便我可以使用更多数据进行训练。鉴于此,我怀疑这一定是某种常见问题,非常感谢有经验/精通使用 RNN/LSTM 的人提供的任何帮助/资源。
解决方法
这里是一个预测未来股价的LSTM模型,但它预测的是第二天的股价,而不是下一秒的股价。我使用这个策略和其他非常相似的策略赚了数百万美元,但赚到几百万需要一点时间,我认为你不会在一秒钟内做到。
from pandas_datareader import data as wb
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from matplotlib.pylab import rcParams
from sklearn.preprocessing import MinMaxScaler
start = '2019-06-30'
end = '2020-06-30'
tickers = ['GOOG']
thelen = len(tickers)
price_data = []
for ticker in tickers:
prices = wb.DataReader(ticker,start = start,end = end,data_source='yahoo')[['Open','Adj Close']]
price_data.append(prices.assign(ticker=ticker)[['ticker','Open','Adj Close']])
#names = np.reshape(price_data,(len(price_data),1))
df = pd.concat(price_data)
df.reset_index(inplace=True)
for col in df.columns:
print(col)
#used for setting the output figure size
rcParams['figure.figsize'] = 20,10
#to normalize the given input data
scaler = MinMaxScaler(feature_range=(0,1))
#to read input data set (place the file name inside ' ') as shown below
df['Adj Close'].plot()
plt.legend(loc=2)
plt.xlabel('Date')
plt.ylabel('Price')
plt.show()
ntrain = 80
df_train = df.head(int(len(df)*(ntrain/100)))
ntest = -80
df_test = df.tail(int(len(df)*(ntest/100)))
#importing the packages
from sklearn.preprocessing import MinMaxScaler
from keras.models import Sequential
from keras.layers import Dense,Dropout,LSTM
#dataframe creation
seriesdata = df.sort_index(ascending=True,axis=0)
new_seriesdata = pd.DataFrame(index=range(0,len(df)),columns=['Date','Adj Close'])
length_of_data=len(seriesdata)
for i in range(0,length_of_data):
new_seriesdata['Date'][i] = seriesdata['Date'][i]
new_seriesdata['Adj Close'][i] = seriesdata['Adj Close'][i]
#setting the index again
new_seriesdata.index = new_seriesdata.Date
new_seriesdata.drop('Date',axis=1,inplace=True)
#creating train and test sets this comprises the entire data’s present in the dataset
myseriesdataset = new_seriesdata.values
totrain = myseriesdataset[0:255,:]
tovalid = myseriesdataset[255:,:]
#converting dataset into x_train and y_train
scalerdata = MinMaxScaler(feature_range=(0,1))
scale_data = scalerdata.fit_transform(myseriesdataset)
x_totrain,y_totrain = [],[]
length_of_totrain=len(totrain)
for i in range(60,length_of_totrain):
x_totrain.append(scale_data[i-60:i,0])
y_totrain.append(scale_data[i,0])
x_totrain,y_totrain = np.array(x_totrain),np.array(y_totrain)
x_totrain = np.reshape(x_totrain,(x_totrain.shape[0],x_totrain.shape[1],1))
In [85]:
#LSTM neural network
lstm_model = Sequential()
lstm_model.add(LSTM(units=50,return_sequences=True,input_shape=(x_totrain.shape[1],1)))
lstm_model.add(LSTM(units=50))
lstm_model.add(Dense(1))
lstm_model.compile(loss='mean_squared_error',optimizer='adadelta')
lstm_model.fit(x_totrain,y_totrain,epochs=10,batch_size=1,verbose=2)
#predicting next data stock price
myinputs = new_seriesdata[len(new_seriesdata) - (len(tovalid)+1) - 60:].values
myinputs = myinputs.reshape(-1,1)
myinputs = scalerdata.transform(myinputs)
tostore_test_result = []
for i in range(60,myinputs.shape[0]):
tostore_test_result.append(myinputs[i-60:i,0])
tostore_test_result = np.array(tostore_test_result)
tostore_test_result = np.reshape(tostore_test_result,(tostore_test_result.shape[0],tostore_test_result.shape[1],1))
myclosing_priceresult = lstm_model.predict(tostore_test_result)
myclosing_priceresult = scalerdata.inverse_transform(myclosing_priceresult)
totrain = df_train
tovalid = df_test
#predicting next data stock price
myinputs = new_seriesdata[len(new_seriesdata) - (len(tovalid)+1) - 60:].values
# Printing the next day’s predicted stock price.
print(len(tostore_test_result));
print(myclosing_priceresult);
结果:
[[1396.532]]
您可以在下面的我的博客中找到其他一些预测未来股票价格的示例。
版权声明:本文内容由互联网用户自发贡献,该文观点与技术仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 dio@foxmail.com 举报,一经查实,本站将立刻删除。