Advanced

Evaluating a Data Mining Model

By Janani Ravi
This course covers the important techniques in model evaluation for some of the most popular types of data mining techniques. These techniques range from association rules learning to clustering, regression, and classification.
Play course overview
Course info
Level
Beginner
Updated
Oct 29, 2019
Duration
2h 45m
Table of contents
Course Overview
Course Overview 2m
Evaluating the Effectiveness of a Clustering Model
Module Overview 2m Prerequisites and Course Outline 1m Evaluating the Results of Data Mining 6m White-box Models and Concept Drift 4m Model Simplicity 5m Evaluating Clustering Models 7m Demo: Performing Clustering Analysis Using K-means Clustering 7m Demo: Performing Clustering Analysis Using Agglomerative Clustering and Mean Shift Clustering 4m Demo: Evaluating K-means Clustering Using Sum of Squared Distances and Silhoutte Score 5m Demo: Evaluating Agglomerative Clustering and Estimating the Right Bandwidth for Mean Shift Clustering 5m Module Summary 2m
Evaluating the Effectiveness of Association Rule Mining
Module Overview 2m Association Rule Mining for Market Basket Analysis 3m Support and Frequent Itemsets 4m Confidence, Lift, and Conviction 8m An Overview of the Apriori Algorithm 3m Demo: Using the Apriori Algorithm to Generate Frequent Itemsets 7m Demo: Association Rule Mining on a Toy Dataset 5m Demo: Exploring the Bread Basket Dataset 4m Demo: Association Rule Mining Using the Bread Basket Data 3m Module Summary 1m
Evaluating the Effectiveness of Regression Models
Module Overview 1m Finding the Best Fit Line 3m Interpreting Regression Results 3m R-square and Adjusted R-square 3m T-statistics and F-statistic 2m Demo: Exploring the Regression Dataset 6m Demo: Building and Evaluating a Regression Model 5m Demo: Interpreting Results Using Residuals and Learning Curves 5m Demo: Evaluating Multiple Regression Models 7m Module Summary 1m
Evaluating the Effectiveness of Classification Models
Module Overview 1m Accuracy as an Evaluation Metric 2m Precision and Recall to Evaluate Classifiers 5m The ROC Curve 5m Validating Models Using Training, Validation, and Test Sets 5m K-fold Cross Validation 3m Demo: Exploring the Classification Dataset 5m Demo: K-fold, Hold-out, and Shuffle Split Cross Validation 6m Demo: Grid Search for Hyperparameter Tuning with Cross Validation 5m Demo: Evaluating the Model Using Accuracy, Precision, Recall and the ROC Curve 3m Module Summary 2m
Description
Course info
Level
Beginner
Updated
Oct 29, 2019
Duration
2h 45m
Description

Data Mining is an umbrella term used for techniques that find patterns in large datasets. Thus, data mining can effectively be thought of as the application of machine learning techniques to big data.

In this course, Evaluating a Data Mining Model, you will gain the ability to answer the two most important questions that every practitioner of data mining must answer - is a particular model valid for this data? And, if yes, what is that model telling us?

First, you will learn that evaluating model fit and interpreting model results are key steps in the data mining process. Next, you will discover how association rules learning - a classic data mining technique - is implemented and evaluated.

Finally, you will round out your knowledge by seeing how the popular ML solution techniques - regression, classification, and clustering - can be implemented and evaluated for fit.

When you’re finished with this course, you will have the skills and knowledge to implement data mining techniques, evaluate them for model fit, and then intelligently interpret their findings.

About the author
Janani Ravi
About the author

A problem solver at heart, Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework.

More from the author
Implementing Machine Learning Workflow with Weka
Intermediate
2h 1m
Dec 11, 2020
Handling Streaming Data with GCP Dataflow
Advanced
3h 12m
Dec 11, 2020
Implementing Machine Learning Workflow with RapidMiner
Intermediate
2h 23m
Dec 8, 2020
More courses by Janani Ravi
Section Introduction Transcripts
Section Introduction Transcripts

Course Overview
Hi, my name is Janani Ravi, and welcome to this course on Evaluating a Data Mining Model. A little about myself, I have a masters degree in electrical engineering from Stanford and have worked at companies such as Microsoft, Google, and Flipkart. At Google, I was one of the first engineers working on real-time collaborative editing in Google Docs, and I hold four patents for its underlying technologies. I currently work on my own startup, Loonycorn, a studio for high-quality video content. Data mining is an umbrella term used for techniques that find patterns in large datasets, thus data mining can effectively be thought of as the application of machine learning techniques to big data. In this course, you will gain the ability to answer the two most important questions that every practitioner of data mining must answer, is a particular model valid for this data, and if yes, what is that model telling us? First, you will learn that evaluating model fit and interpreting model results are key steps in the data mining process. Next, you will discover how association rules learning, a classic data mining technique, is implemented and evaluated. Finally, you'll round out your knowledge by seeing how the popular ML solution techniques, regression, classification, and clustering, can be implemented and evaluated for fit. When you're finished with this course, you will have the skills and knowledge to implement data mining techniques, evaluate them for model fit, and then intelligently interpret their findings.

You're the smartest person in the room

PROVE IT

Your team won't just close the skills gap

THEY'LL HURDLE IT