UNCC Online FinTech Bootcamp Module 14

As a financial advisor I will enhance existing trading signals with machine learning algorithms that can adapt to new data. I’ll combine my new algorithmic trading skills with my existing skills in financial Python programming and machine learning to create an algorithmic trading bot that learns and adapts to new data and evolving markets.

This application is written in Python 3.7 using JupyterLab version 3.0.14.

Import the following libraries:

• pandas (an open source, BSD-licensed library providing high-performance, easy-to-use data structures and data analysis tools for the Python programming language.)
• Pathlib (a library that enables consistent input and output of files from the main app.)
• scikit-learn (an open source machine learning library that supports supervised and unsupervised learning.)
• numpy (a Python library that adds support for large, multi-dimensional arrays and matrices, along with a large collection of high-level mathematical functions to operate on these arrays.)
• hvplot.pandas (a high-level plotting API for the PyData ecosystem built on HoloViews.)
• matplotlib.pyplot (a state-based interface to matplotlib. It provides an implicit, MATLAB-like, way of plotting.)

The machine_learning_trading_bot.ipynb notebook will be used to complete the following tasks:

• Implement an algorithmic trading strategy that uses machine learning to automate the trade decisions.
• Adjust the input parameters to optimize the trading algorithm.
• Train a new machine learning model and compare its performance to that of a baseline model.

After comparing the baseline to the other SVM models it is evident that the version with an offset of 6 months is more precise than the other 2 models. Thus, I would recommend the version with an offset of 6 months.

Chancie Altham

MIT License