Scribd
Upload
39 views1 page

Machine Learning Trading Signal Model

The document outlines a process for developing a trading strategy using machine learning and LSTM models. It includes feature engineering to add technical indicators like ATR, RSI, and MACD to the dataset. Additionally, it describes the training of a RandomForestClassifier and the construction of an LSTM model for making predictions.

Uploaded by

vsvk034
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
39 views1 page

Machine Learning Trading Signal Model

The document outlines a process for developing a trading strategy using machine learning and LSTM models. It includes feature engineering to add technical indicators like ATR, RSI, and MACD to the dataset. Additionally, it describes the training of a RandomForestClassifier and the construction of an LSTM model for making predictions.

Uploaded by

vsvk034
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd

import numpy as np

import talib
from [Link] import RandomForestClassifier
from [Link] import Sequential
from [Link] import LSTM, Dense, Dropout

# --- Feature Engineering ---


def add_indicators(df):
df['ATR'] = [Link](df['high'], df['low'], df['close'], timeperiod=14)
df['RSI'] = [Link](df['close'], timeperiod=14)
df['MACD'], df['MACD_signal'], _ = [Link](df['close'], 12, 26, 9)
return df

# --- ML-Based Trading Signal ---


def train_ml_model(df):
df = add_indicators(df)
[Link](inplace=True)
X = df[['ATR', 'RSI', 'MACD', 'MACD_signal']]
y = [Link](df['close'].shift(-1) > df['close'], 1, 0)
model = RandomForestClassifier(n_estimators=100)
[Link](X, y)
return model

# --- LSTM Model for Prediction ---


def build_lstm_model():
model = Sequential([
LSTM(50, return_sequences=True, input_shape=(30, 4)),
Dropout(0.2),
LSTM(50, return_sequences=False),
Dense(25, activation='relu'),
Dense(1, activation='sigmoid')
])
[Link](optimizer='adam', loss='binary_crossentropy',
metrics=['accuracy'])
return model

You might also like