About this Course

10,153 recent views
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Flexible deadlines
Reset deadlines in accordance to your schedule.
Beginner Level

Accessible to business-side learners yet also vital to techies. Engage in the commercial use of ML – whether you're an enterprise leader or a quant.

Approx. 16 hours to complete
English

Skills you will gain

Data ScienceArtificial Intelligence (AI)Machine LearningPredictive AnalyticsMachine Learning (ML) Algorithms
Shareable Certificate
Earn a Certificate upon completion
100% online
Start instantly and learn at your own schedule.
Flexible deadlines
Reset deadlines in accordance to your schedule.
Beginner Level

Accessible to business-side learners yet also vital to techies. Engage in the commercial use of ML – whether you're an enterprise leader or a quant.

Approx. 16 hours to complete
English

Offered by

Placeholder

SAS

Syllabus - What you will learn from this course

Week
1

Week 1

5 hours to complete

MODULE 1 - The Foundational Underpinnings of Machine Learning

5 hours to complete
10 videos (Total 83 min), 5 readings, 12 quizzes
10 videos
P-hacking: a treacherous pitfall8m
P-hacking: your predictive insights may be bogus8m
P-hacking: how to ensure sound discoveries9m
Avoiding overfitting: the train/test split8m
Why ice cream is linked to shark attacks7m
Causation is just a hobby -- prediction is your job6m
The art of induction: why generalizing from data is hard6m
Learning from mistakes: why negative cases matter5m
Intro to the hands-on assessment (Excel or Google Sheets)11m
5 readings
Why this course isn't hands-on & why it's essential for techies anyway19m
One-question survey1m
Complementary materials on p-hacking (optional)10m
Correlation does not imply causation (optional)10m
Data access for auditors (optional)10m
11 practice exercises
Course overview: Machine Learning Under the Hood4m
P-hacking: a treacherous pitfall2m
P-hacking: your predictive insights may be bogus2m
P-hacking: how to ensure sound discoveries4m
Avoiding overfitting: the train/test split4m
Why ice cream is linked to shark attacks4m
Causation is just a hobby -- prediction is your job4m
The art of induction: why generalizing from data is hard4m
Learning from mistakes: why negative cases matter2m
Intro to the hands-on assessment (Excel or Google Sheets)2m
Module 1 Review30m
Week
2

Week 2

3 hours to complete

MODULE 2 - Standard, Go-To Machine Learning Methods

3 hours to complete
12 videos (Total 107 min), 1 reading, 11 quizzes
12 videos
Business rules rock and decision trees rule13m
Pruning decision trees to avoid overfitting12m
DEMO - Comparing decision tree models (optional)13m
Drawing the gains curve for a decision tree6m
Drawing the profit curve for a decision tree6m
Naïve Bayes11m
Linear models and perceptrons6m
Linear part II: a perceptron in two dimensions8m
Why probabilities drive better decisions than yes/no outputs7m
Logistic regression6m
DEMO - Training a logistic regression model (optional)4m
1 reading
A powerful, helpful visualization of how decision trees work (optional)10m
11 practice exercises
A refresher on decision trees2m
Business rules rock and decision trees rule4m
Pruning decision trees to avoid overfitting2m
Drawing the gains curve for a decision tree2m
Drawing the profit curve for a decision tree2m
Naïve Bayes2m
Linear models and perceptrons2m
Linear part II: a perceptron in two dimensions4m
Why probabilities drive better decisions than yes/no outputs4m
Logistic regression4m
Module 2 Review30m
Week
3

Week 3

4 hours to complete

MODULE 3 - Advanced Methods, Comparing Methods, & Modeling Software

4 hours to complete
16 videos (Total 154 min), 2 readings, 14 quizzes
16 videos
Neural nets: decision boundaries & a comparison to logistic regression8m
DEMO - Training a neural network model (optional)2m
Deep learning9m
Ensemble models and the Netflix Prize8m
Supercharging prediction: ensembles & the generalization paradox12m
DEMO - Training an ensemble model (optional)3m
DEMO - Autotuning a machine learning model (optional)3m
Compare and contrast: summary of ML methods8m
Machine learning software: dos and don'ts for choosing a tool11m
Machine learning software: how tools vary and how to choose one11m
Model deployment: out of the software tool and into the field9m
Uplift modeling I: optimize for influence and persuade by the numbers12m
Uplift modeling II: modeling over treatment and control groups12m
Uplift modeling III: how it works – for banks and for Obama15m
Uplift modeling IV: improving churn modeling, plus other applications13m
2 readings
The generalization paradox of ensembles (optional) 10m
Complementary readings on uplift modeling (optional) 10m
14 practice exercises
How neural networks work5m
Neural nets: decision boundaries & a comparison to logistic regression2m
Deep learning2m
Ensemble models and the Netflix Prize2m
Supercharging prediction: ensembles & the generalization paradox4m
Compare and contrast: summary of ML methods4m
Machine learning software: dos and don'ts for choosing a tool2m
Machine learning software: how tools vary and how to choose one2m
Model deployment: out of the software tool and into the field2m
Uplift modeling I: optimize for influence and persuade by the numbers2m
Uplift modeling II: modeling over treatment and control groups2m
Uplift modeling III: how it works – for banks and for Obama4m
Uplift modeling IV: improving churn modeling, plus other applications4m
Module 3 Review30m
Week
4

Week 4

4 hours to complete

MODULE 4 – Pitfalls, Bias, and Conclusions

4 hours to complete
7 videos (Total 76 min), 8 readings, 8 quizzes
7 videos
Machine bias II: visualizing why models are inequitable8m
Machine bias III: justice can't be colorblind13m
Explainable ML, model transparency, and the right to explanation15m
Conclusions on ML ethics: establishing standards as a form of social activism8m
Pitfalls: the seven deadly sins of machine learning11m
Conclusions and what's next – continuing your learning10m
8 readings
The original ProPublica article on machine bias10m
Interactive MIT Technology Review article on disparate false positive rates10m
Another interactive demo of machine bias (optional)10m
Complementary reading on machine bias (optional)10m
More on explainable ML and model transparency (optional)10m
Tallying the positive and negative impacts of AI (optional)10m
John Elder's top ten data science mistakes (optional)10m
Further resources and readings to continue your learning (optional)10m
8 practice exercises
Machine bias I: the conundrum of inequitable models4m
Machine bias II: visualizing why models are inequitable2m
Machine bias III: justice can't be colorblind4m
Explainable ML, model transparency, and the right to explanation4m
Conclusions on ML ethics: establishing standards as a form of social activism2m
Pitfalls: the seven deadly sins of machine learning4m
Conclusions and what's next - continuing your learning2m
Module 4 Review30m

Reviews

TOP REVIEWS FROM MACHINE LEARNING UNDER THE HOOD: THE TECHNICAL TIPS, TRICKS, AND PITFALLS

View all reviews

About the Machine Learning for Everyone with Eric Siegel Specialization

Machine Learning for Everyone with Eric Siegel

Frequently Asked Questions

More questions? Visit the Learner Help Center.