Overview
The first step to building a deep learning trading model (see machine learning process) is to extract the necessary features of the data that the model will train on. This process is typically known as feature extraction.
Starting from an array of data, the feature extraction process will use Array Transformations to tranform the dataset to one that can be used by tensor-flow.
Transformations
Transforming the model training set generally needs to account for the following.
- Indicators - the feature extraction process needs to calculate any indicators that will be used by the model to generate trade signals.
- Input Format - the data needs to be transformed into a format that can be used as input to the model chosen. For deep learning models, the inputs are typically structured as column vectors, usually represented as an array.