Python & Machine Learning for Financial Analysis

Python & Machine Learning for Financial Analysis

What you’ll learn

• Master Python 3 programming fundamentals for Data Science and Machine Learning with focus on Finance.
• Understand how to leverage the power of Python to apply key financial concepts such as calculating daily portfolio returns, risk and Sharpe ratio.
• Understand the theory and intuition behind Capital Asset Pricing Model (CAPM), Markowitz portfolio optimization, and efficient frontier.
• Apply Python to implement several trading strategies such as momentum-based and moving average trading strategies.
• Understand how to use Jupyter Notebooks for developing, presenting and sharing Data Science projects.
• Learn how to use key Python Libraries such as NumPy for scientific computing, Pandas for Data Analysis, Matplotlib for data plotting/visualization, and Seaborn for statistical plots.
• Master SciKit-Learn library to build, train and tune machine learning models using real-world datasets.
• Apply machine and deep learning models to solve real-world problems in the banking and finance sectors such as stock prices prediction, security news sentiment analysis, credit card fraud detection, bank customer segmentation, and loan default prediction.
• Understand the theory and intuition behind several machine learning algorithms for regression tasks (simple/multiple/polynomial), classification and clustering (K-Means).
• Assess the performance of trained machine learning regression models using various KPI (Key Performance indicators) such as Mean Absolute Error, Mean Squared Error, and Root Mean Squared Error intuition, R-Squared intuition, and Adjusted R-Squared.
• Assess the performance of trained machine learning classifiers using various KPIs such as accuracy, precision, recall, and F1-score.
• Understand the underlying theory, intuition and mathematics behind Artificial Neural Networks (ANNs), Recurrent Neural Networks (RNNs) and Long Short Term Memory Networks (LSTM).
• Train ANNs using back propagation and gradient descent algorithms.
• Optimize ANNs hyper parameters such as number of hidden layers and neurons to enhance network performance.
• Master feature engineering and data cleaning strategies for machine learning and data science applications.