Back To Course Home

Business Machine Learning

0% completed

Course Introduction

About This Course

Linear Regression

Introduction to Linear Regression

Welcome and Data Overview

Exploratory Data Analysis

Variance and Covariance

Machine Learning

Model Evaluation

Model Explainability

Finalizing and Serializing the Model

Model Deployment in the Notebook

Cross-validation

Exercise: Model the Boston Housing Dataset

Solution: Model the Boston Housing Dataset

Exercise: Model the King County's House Sales Dataset

Solution: Model the King County's House Sales Dataset

Quiz: Linear Regression

Regularization

Introduction to Regularization Penalties Effect of Regularization Model Performance Summary Quiz: Regularization

Bias-Variance Trade-off

Introduction and Data Generation Morale Function and Model Error Generating Student Samples and Plot Model Building to Predict the Morale Bias-Variance Trade-off Summary Quiz: Bias Variance Trade-off

Categorical Features

Quantitative vs. Qualitative Data and Creating Dummies Redundant Variables and Machine Learning Summary Exercise: Model the Auto MPG Dataset Solution: Model the Auto MPG Dataset Quiz: Categorical Features

Logistic Regression

Introduction to Logistic Regression Probability and Odds Understanding Logistic Regression Logistic Regression Implementation Model Evaluation Summary Quiz: Logistic Regression

Logistic Regression: Titanic Data

The Dataset and Exploratory Data Analysis Data Preprocessing Getting Data Ready and Building Machine Learning Model Predictions and Evaluation Model Evaluation Feature Importance and Model Explainability Summary Exercise: Retrain the Model Without Pclass Dummies Solution: Retrain the Model Without Pclass Dummies Quiz: Logistic Regression—Titanic Data

Multiclass Classification and Handling Imbalanced Classes

Introduction to Multiclass Logistic Regression Classification Imbalanced Datasets and Techniques to Handle Them Machine Learning and Imbalanced Data Performance of the Trained Models on Unseen Data Summary Quiz: Multiclass Classification and Handling Imbalanced Classes

Project: Predicting Chronic Kidney Disease

Problem Definition and the Data Exploratory Data Analysis Data Preprocessing Model Training and Evaluation

K-Nearest Neighbors

Introduction to K-Nearest Neighbors Working Principle of K-Nearest Neighbors Visualize the Working of K-Nearest Neighbors Final Thoughts Quiz: K-Nearest Neighbors

Implementation of K-Nearest Neighbors

The Dataset and Exploratory Data Analysis

Model Training Using Unscaled Data

Effect of Feature Scaling

Model Training Using Scaled Features

Elbow Method to Chose the K Value

Model Comparisons

Quiz: Implementation of K-Nearest Neighbors

Logistic Regression vs. KNN

The Dataset and Exploratory Data Analysis Baseline Accuracy and Machine Learning Model Selection Exercise: Find the Best Combination of Parameters Solution: Find the Best Combination of Parameters Exercise: Find the Best Value for K Solution: Find the Best Value for K

Decision Tree Learning

Introduction to Decision Trees Bootstrap, Bagging, and Random Forests The Dataset and Exploratory Data Analysis Machine Learning Feature Importance Hyperparameters and Their Tuning ROC Curve Playing With Probability Cut-off Tree Visualization Exercise: Train a Decision Tree Model Using the Gini Criteria Solution: Train a Decision Tree Model Using the Gini Criteria Exercise: Train a Random Forest Model Using the Entropy Criteria Solution: Train a Random Forest Model Using the Entropy Criteria Quiz: Decision Tree Learning

Bootstrapping and Confidence Interval

Introduction to Bootstrapping and Confidence Interval The Data Confidence Interval of Mean Confidence Interval for the Median Quiz: Bootstrapping and Confidence Interval

Support Vector Machine

Introduction to Support Vector Machine Visualize the Working of the Support Vector Machine The Dataset and Exploratory Data Analysis Feature Selection Machine Learning Grid Search Feature Scaling ROC Curve and Saving the Model Quiz: Support Vector Machine

Practice and Comparisons

MNIST: Handwritten Digits Dataset The Iris Dataset The Circles Dataset

What's Next?

Final Thoughts and Future Directions

Appendix

R-square and Goodness of the Fit

Elbow Method to Chose the K Value

Learn how to choose a better k value to improve our modeling.

We'll cover the following

Elbow method
Plotting accuracy

Let’s explore if we can improve the model using a better value of $k$ .

Elbow method

To do this, we can use the elbow method to find a good value for $k$ . We iterate a range of KNN models using different $k$ values in the elbow method. Let’s try using the odd value of $k$ . We get the error rate for every $k$ value and plot it against $k$ to find its optimum value.

Get hands-on with 1400+ tech skills courses.