Applied Machine Learning
Apply custom machine learning algorithms with Python
Machine Learning for Finance Professionals
Become one of the few in the Finance Industry that can write & use real patented algorithm algorithms to advise Fortune 500 companies on investment banking and capital markets decisions. By the end of the course, you will be trained to identify the ideal opportunities to apply this technology in your specific environment, so that you can immediately use your new skills to make an impact on your team.
is the ideal next step for those interested in furthering their foundational Python skills. This is an advanced course that utilizes concepts learned from the Python Fundamentals course and combines them with popular machine learning algorithms from the popular Scikit-Learn Machine Learning Package to solve real-world business problems. Although this course can be taken by any business professional, it is catered for those interested in furthering their career in the following specialties:
Investment Banking
Sales & Trading
Capital Markets
Asset Management
Treasury Management
Corporate Development
You will master cutting-edge skills that will enable you to deliver meaningful results in your professional environment:
With multiple exercises and real case studies
Liquidity Regressor Model
This model will help advise large corporations on raising capital. Corporations often ask for advice about how much liquidity they should maintain and how they stack up against peer companies. You will use 5 different regression algorithms to find the optimal solution based on a set of inputs.
Investor Classifier Model
This model is an altered version of a real machine learning algorithm used by top investment banks to predict investor behavior when raising capital for large corporate clients. You will learn to use 4 different classification algorithms to determine which investors to invite to participate in the deal and how much capital you should invite them to commit.
Learning Objectives
Download Exercise Notebook ML01
1a - The Machine Learning Process
1b - Matplotlib and Seaborn
1c - A Few Quick Notes
1d - Exercise
1e - Solution
1f - Countplot Function
1g - Exercise
1h - Solution
1i - Replace Function and Sparse Classes
1j - Exercise
1k - Solution
1l - Exercise
1m - Solution
1n - Spotting Outliers
1o - Exercise
1p - Solution
1q - Exercise
1r - Solution
1s - Exercise
1t - Solution
1u - Exercise
1v - Solution
1w - Exercise
1x - Solution
1y - NaN Object
1z - Exercise
1aa - Solution
1ab - Dropping Null Values
1ac - Exercise
1ad - Solution
1ae - Boxplots with Seaborn
1af - Exercise
1ag - Solution
1ah - Saving Your DataFrame
1ai - Review
Learning Objectives
2a - What Are Regression Algorithms?
2b - Real Relationships and Overfitting
2c - Preventing Overfitting with Regularization
2d - Decision Trees and Ensemble Methods
Learning Objectives
Download Exercise Notebook ML03
3a - Case Study Overview
3b - Exercise
3c - Solution
3d - Metadata
3e - Exercise
3f - Solution
3g - Splitting Your Data
3h - Exercise
3i - Solution
3j - train_test_split() Function
3k - Unpacking Lists
3l - Exercise
3m - Solution
3n - Progress Checkpoint
3o - Model Pipelines
3p - Exercise
3q - Solution
3r - Progress Checkpoint
3s - Hyperparameter Tuning
3t - Exercise
3u - Solution
3v - Exercise
3w - Solution
3x - Aggregating Hyperparameter Grids
3y - Progress Checkpoint
3z - Cross Validation
3aa - Creating Untrained Models
3ab - Exercise
3ac - Solution
3ad - Training and Tuning Models
3ae - Exercise
3af - Solution
3ag - Model Evaluation
3ah - Exercise
3ai - Solution
3aj - Progress Checkpoint
3ak - Visualizing Model Predictions
3al - Exercise
3am - Solution
3an - Using Your Model
3ao - Review
Learning Objectives
4a - Binary Classification
4b - Logistic Regression
4c - Decision Tree Classifiers
Learning Objectives
Download Exercise Notebook ML05
5a - Case Study Overview
5b - Exercise
5c - Solution
5d - Metadata
5e - Exercise
5f - Solution
5g - One Error
5h - Exercise
5i - Solution
5j - Countplot of Investors
5k - Exercise
5l - Solution
5m - Exploring Relationships
5n - Exercise
5o - Solution
5p - Reviewing Your Results
5q - Feature Engineering
5r - Exercise
5s - Solution
5t - Reviewing tier_change
5u - Controlling for Demotions
5v - Exercise
5w - Solution
5x - Analyzing Goldman Sachs
5y - Exercise
5z - Solution
5aa - Seaborn .Implot() Function
5ab - Exercise
5ac - Solution
5ad - Review
Learning Objectives
Download Exercise Notebook ML06
6a - Import Packages & Data
6b - Exercise
6c - Solution
6d - Dummy Variables
6e - Exercise
6f - Solution
6g - Remove Redundant Target
6h - Splitting Data
6i - Exercise
6j - Solution
6k - Model Pipelines
6l - Exercise
6m - Solution
6n - Validating Pipelines
6o - Hyperparameter Tuning
6p - Exercise
6q - Solution
6r - Validating Hyperparameter Grids
6s - Cross Validation
6t - Exercise
6u - Solution
6v - Fitting Untrained Models
6w - Exercise
6x - Solution
6y - AUROC Metric (Area Under ROC)
6z - Confusion Matrix
6aa - Perfect AUROC
6ab - Calculating AUROC
6ac - Exercise
6ad - Solution
6ae - Review
In-Person and Webinar-Based Marquee Courses