Course Outline
1. Introducing Machine Learning
- Defining Machine Learning
- How it expands upon data analysis
-
Typical business applications:
- Sales forecasting
- Customer segmentation
- Churn prediction
2. Transitioning from Data Analysis to Machine Learning
- Review: managing data in Pandas
- Shifting from descriptive to predictive analysis
- Defining a Machine Learning challenge
3. Streamlined Machine Learning Workflow
- Dataset preparation
- Data splitting (training versus testing sets)
- Model training
- Generating predictions
4. Preparing Data for Machine Learning
- Addressing missing values
- Encoding categorical variables
- Feature selection (introductory level)
- Scaling (conceptual overview)
5. Supervised Learning (Practical Application)
Regression
- Linear Regression
- Application: forecasting numerical values (e.g., sales, demand)
Classification
- Logistic Regression
- Application: binary outcomes (e.g., churn, fraud detection)
6. Unsupervised Learning
Clustering
- K-means clustering
- Application: customer segmentation
7. Model Evaluation (Streamlined)
- Comparing training and testing performance
- Accuracy (for classification tasks)
- Fundamental understanding of error (for regression tasks)
8. Interpreting Outcomes
- Understanding model outputs
- Recognizing patterns and trends
- Converting results into business insights
9. Practical End-to-End Case Study
- Loading the dataset
- Preparing and cleaning data
- Training a model
- Evaluating performance
- Extracting insights
Requirements
Requirements
- Foundational knowledge of Python
- Proficiency with Pandas and dataset management
- Understanding of fundamental data analysis principles
Intended Audience
- Data Analysts
- Business Analysts with foundational Python skills
- Professionals who have finished the Python for Data Analysis course or possess equivalent expertise
- Individuals new to Machine Learning
Testimonials (1)
I really liked the end where we took the time to play around with CHAT GPT. The room was not set up the best for this- instead of one large table a couple of small ones so we could get into small groups and brainstorm would have helped
