{"id":191549,"date":"2023-06-07T10:52:34","date_gmt":"2023-06-07T14:52:34","guid":{"rendered":"https:\/\/ibkrcampus.com\/?p=191549"},"modified":"2023-06-07T10:52:36","modified_gmt":"2023-06-07T14:52:36","slug":"deep-learning-artificial-neural-network-using-tensorflow-in-python","status":"publish","type":"post","link":"https:\/\/www.interactivebrokers.com\/campus\/ibkr-quant-news\/deep-learning-artificial-neural-network-using-tensorflow-in-python\/","title":{"rendered":"Deep Learning – Artificial Neural Network Using TensorFlow In Python"},"content":{"rendered":"\n

Originally posted on QuantInsti<\/a> blog.<\/em><\/p>\n\n\n\n

You can also download the python code and dataset from my github a\/c<\/a><\/pre>\n\n\n\n
Excerpt<\/em><\/strong><\/p>\n\n\n\n
In this article, we are going to develop a machine learning technique called Deep learning (Artificial Neural network) by using tensor flow and predicting stock price in python. At the end of this article you will learn how to build artificial neural network by using tensor flow and how to code a strategy using the predictions from the neural network.<\/p>\n\n\n\n
System Requirements: Python 3.6<\/strong><\/p>\n\n\n\n
If you are new to Neural Networks and would like to gain an understanding of their working, I would recommend you to go through the following blogs before building a neural network.<\/p>\n\n\n\n
Working of neural networks for stock price prediction<\/a><\/p>\n\n\n\n
Training neural networks for stock price prediction<\/a><\/p>\n\n\n\n
Coding The Strategy<\/strong><\/h3>\n\n\n\n
Importing Libraries<\/strong><\/h4>\n\n\n\n
We will start by importing all libraries. Please note if the below library not installed yet you need to install 1st in anaconda prompt before importing.<\/p>\n\n\n\n
\"\"<\/figure>\n\n\n\n
TensorFlow<\/strong> is an open-source software library for dataflow programming across a range of tasks. It is a symbolic math library, and is used for machine learning applications such as deep learning<\/a> neural networks. Wikipedia<\/a>.<\/p>\n\n\n\n
Numpy<\/strong> 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<\/strong> will help us in using the powerful dataframe object, which will be used throughout the code for building the artificial neural network in Python<\/a>.<\/p>\n\n\n\n
Scikit-learn<\/strong> is a free software machine learning library for the Python programming language. It features various classification, regression<\/a> and clustering algorithms including support vector machines<\/a>. Wikipedia<\/a><\/p>\n\n\n\n
Matplotlib<\/strong> is a Python 2D plotting library which produces publication quality figures in a variety of hardcopy formats and interactive environments across platforms<\/p>\n\n\n\n
Talib<\/strong> is a technical analysis library, which will be used to compute the RSI and Williams %R. These will be used as features for training our artificial neural network. We could add more features using this library.<\/p>\n\n\n\n
Importing the dataset<\/strong><\/h4>\n\n\n\n
We are going to use daily OHLC data for the stock of Tata Motors trading on NSE for the time period from 1st January 2000 to 30 Aug 2018. We 1st import our dataset .CSV file named \u2018TATAMOTORS.NS.csv\u2019 saved in personal drive in your computer. This is done using the pandas library, and the data is stored in a dataframe named dataset. We then drop the missing values in the dataset using the dropna() function. We choose only the OHLC data from this dataset, which would also contain the Date, Adjusted Close and Volume data. We will be building our input features by using only the OHLC values.<\/p>\n\n\n\n
Please note you can also download these data from my github.<\/p>\n\n\n\n
\"\"<\/figure>\n\n\n\n
Preparing the dataset<\/strong><\/h4>\n\n\n\n
We then prepare the various input features which will be used by the artificial neural network to train itself for making the predictions. Please note I have limited to only below 8 features, however you should create more to get more accurate result.<\/p>\n\n\n\n