{"id":191306,"date":"2023-06-02T10:28:10","date_gmt":"2023-06-02T14:28:10","guid":{"rendered":"https:\/\/ibkrcampus.com\/?p=191306"},"modified":"2023-06-02T17:01:17","modified_gmt":"2023-06-02T21:01:17","slug":"neural-network-in-python-types-structure-and-trading-strategies-part-iii","status":"publish","type":"post","link":"https:\/\/www.interactivebrokers.com\/campus\/ibkr-quant-news\/neural-network-in-python-types-structure-and-trading-strategies-part-iii\/","title":{"rendered":"Neural Network In Python: Types, Structure And Trading Strategies – Part III"},"content":{"rendered":"\n

Get a general introduction to a neuron with Part I<\/a><\/em> and learn how to train a neural network with Part II.<\/a><\/em><\/p>\n\n\n\n

Neural network in trading<\/h2>\n\n\n\n

Neural networks help you develop strategies based on your overall investment strategy \u207d\u00b9<\/a>\u207e. Whether it is high-risk and growth-focused (short-term trades) or a conservative approach for long-term investment, it all depends on the kind of trading strategy.<\/p>\n\n\n\n

For example, you wish to find a few stocks with particular growth performance or an upward price trend over a period of one year. Now, the neural network can figure out such stocks for your portfolio and hence, make your work easy.<\/p>\n\n\n\n

Also, you can give a number of such parameters or necessary pointers to the neural network so that you have exactly what you are looking for with less effort and time.<\/p>\n\n\n\n

\n\n\n\n

Neural network strategy in Python<\/h2>\n\n\n\n

Let us now see the strategical representation with neural networks in Python.<\/p>\n\n\n\n

First of all we will import libraries.<\/p>\n\n\n\n

Step 1: Importing Libraries<\/h3>\n\n\n\n

We will start by importing a few libraries<\/a>, the others will be imported as and when they are used in the program at different stages. For now, we will import the libraries which will help us in importing and preparing the dataset for training and testing the model.<\/p>\n\n\n\n

import numpy as np\nimport pandas as pd\nimport talib<\/pre>\n\n\n\n
Importing_libraries.py <\/a>hosted with \u2764 by GitHub<\/a><\/p>\n\n\n\n
Numpy is a fundamental package for scientific computing, we will be using this library for computations on our dataset. The library is imported using the alias np.<\/p>\n\n\n\n
Pandas will help us in using the powerful dataframe object, which will be used throughout the code for building the artificial neural network in Python.<\/p>\n\n\n\n
Ta-lib<\/a> is a technical analysis library, which will be used to compute the RSI and Williams %R. These will be used as features in order to train our artificial neural network or ANN. We could add more features using this particular library.<\/p>\n\n\n\n
Step 2: Fetching data from yahoo finance<\/h3>\n\n\n\n
# Setting the random seed to a fixed number\nimport random\n# Setting the random seed to a fixed number\n\nimport random\nrandom.seed(42)<\/pre>\n\n\n\n
Random_seed.py <\/a>hosted with \u2764 by GitHub<\/a><\/p>\n\n\n\n
Random is used to initialise the seed to a fixed number. This is such that every time we run the code we start with the same seed.<\/p>\n\n\n\n
# Download the price data of Apple from November 2019 to January 2023\n# Set the ticker as 'AAPL' and specify the start and end dates\n\nprice_AAPL= yf.download('AAPL', start='2017-11-06', end='2023-01-03', auto_adjust = True)<\/pre>\n\n\n\n
Fetch_AAPL_data.py <\/a>hosted with \u2764 by GitHub<\/a><\/p>\n\n\n\n
We have taken Apple\u2019s data for the time period 6th November 2017 to 3rd January 2023.<\/p>\n\n\n\n
Step 3: Preparing the dataset<\/h3>\n\n\n\n
We will be building our input features by using only the OHLC values. This dataset will help us to specify the features for training our neural network in the next step.<\/p>\n\n\n\n
# Preparing the dataset\nprice_AAPL['H-L'] = price_AAPL['High'] - price_AAPL['Low']\nprice_AAPL['O-C'] = price_AAPL['Close'] - price_AAPL['Open']\nprice_AAPL['3day MA'] = price_AAPL['Close'].shift(1).rolling(window = 3).mean()\nprice_AAPL['10day MA'] = price_AAPL['Close'].shift(1).rolling(window = 10).mean()\nprice_AAPL['30day MA'] = price_AAPL['Close'].shift(1).rolling(window = 30).mean()\nprice_AAPL['Std_dev']= price_AAPL['Close'].rolling(5).std()\nprice_AAPL['RSI'] = talib.RSI(price_AAPL['Close'].values, timeperiod = 9)\nprice_AAPL['Williams %R'] = talib.WILLR(dataset['High'].values, price_AAPL['Low'].values, price_AAPL['Close'].values, 7)<\/pre>\n\n\n\n
Preparing_dataset.py <\/a>hosted with \u2764 by GitHub<\/a><\/p>\n\n\n\n
Step 4: Defining input features from dataset<\/h3>\n\n\n\n
We then prepare the various input features which will be used by the artificial neural network learning<\/a> for making the predictions. We define the following input features:<\/p>\n\n\n\n