Complete Summary for Data Science Methods for MADS (All Lectures + Exam)
32 views 2 purchases
Course
Data Science Methods for MADS (EBM215A05)
Institution
Rijksuniversiteit Groningen (RuG)
The best complete summary for Data Science Methods for MADS (EBM215A05), it includes: All Lectures and the latest Practice Exam. Enhanced with a dynamic table of contents and meticulous organization for readability and easy studying. 100% of profit from this summary is donated to local Groningen NG...
SUMMARY OF EVERYTHING YOU NEED
ALL LECTURES + EXAM 2021-22
E n h a n c e d w i t h a d y n a m ic t a b le o f c o n t e n t s .
, MADS MADLAD |2
Note from MADS MADLAD:
Thank you for buying my summary. I sincerely hope it helps you excel and learn
from this course. When I was writing these I sometimes struggled with this
program, but there were no summaries available.
This is why I decided to write something that is truly complete with a lot of
effort put into it. It helped me and my friends get good grades, but I also
always had you in mind, the future reader. When necessary, I always went the
extra mile to make this summary, more readable, organized and complete.
If you feel like it, leave me a review of how the course is going using this
summary, it will make my day to hear your opinion good or bad!
Check out my other extensive summaries for other MADS courses:
Available on:
Contact info:
If you need help or have an inquiry, contact me: https://www.georgedreemer.com
Connect with me on LinkedIn: https://www.linkedin.com/in/georgedreemer/
Donations:
By no means am I looking for fellow students to send me money! But if you feel like sending
me some ETH or BTC, you can do so here:
--> ETH: 0x123e086c6808459e7fC6Ac7F64a77dBA1dDe0149
--> BTC: bc1qgwzc82vph5v8rmzef4ywechjf85772n7m2e22g
, MADS MADLAD |3
wishes you good luck & perseverance.
Grades Testimony:
, MADS MADLAD |4
Table of Contents
Week 1............................................................................................................... 8
Lecture 1: Introduction to Machine Learning .................................................. 8
Data Science Process ................................................................................... 8
Criteria for a good model ............................................................................. 9
What is (Machine) Learning? ....................................................................... 9
3 Types of ML Models ................................................................................ 10
ML Techniques........................................................................................... 11
Why ML?.................................................................................................... 12
Statistics vs. ML vs. AI ................................................................................ 12
ML Modelling Process (3 Steps) ................................................................. 12
ML Model Process – In Practice: Learning to filter spam............................ 14
Assessing the ML Process .......................................................................... 16
Overfitting & Underfitting.......................................................................... 17
Measures for assessing model quality ....................................................... 18
Data (pre-)processing ................................................................................ 18
Goal of Data Exploration ............................................................................ 18
Steps in Data Exploration ........................................................................... 19
Logistic Regression..................................................................................... 19
Estimation – Beta’s (β) ............................................................................... 21
Interpretation ............................................................................................ 21
In Practice – Titanic Data ........................................................................... 22
Deciding on IVs .......................................................................................... 23
Model Validation (1) – Making Predictions (in R) ....................................... 23
Model Validation (2) – 3 Forms of Validation Criteria ................................ 23
Hit Rate (1) – Interpretation & Calculation ................................................ 23
Hit Rate (2) – How to in R........................................................................... 24
Top Decile Lift (1) – Interpretation & Calculation ....................................... 24
Top Decile Lift (2) – How to in R ................................................................. 25
Top Decile Lift (3) - Lift Curve: Interpretation ............................................ 25
, MADS MADLAD |5
Top Decile Lift (3) - Lift Curve: How to in R................................................. 25
GINI Coefficient (1) – Interpretation & Calculation .................................... 26
GINI Coefficient (2) – How to in R .............................................................. 26
Fit Criteria (1) – Calculation ....................................................................... 26
Fit Criteria (2) – Calculation: Solving overfitting ......................................... 26
Fit Criteria (3) – How to in R ....................................................................... 27
Balanced vs. Unbalanced Sample............................................................... 27
Week 2............................................................................................................. 28
Lecture 2: Stepwise LR, Tree models, Bagging, and Boosting ........................ 28
Overview: Boosting & Bagging techniques................................................. 28
Stepwise Logistic Regression (SLR) ............................................................. 28
3 Types of Stepwise Regressions................................................................ 29
SLR – How to in R ....................................................................................... 29
Tree Models – Decision Trees .................................................................... 30
How to grow a tree: Splitting logic & rules................................................. 31
Splitting Rule for CHAID ............................................................................. 31
Splitting Rule for CART ............................................................................... 32
Splitting rule for C4.5 ................................................................................. 34
Which splitting rule is the best? ................................................................. 34
Regression-type Problem: CART or CHAID? ............................................... 35
Comparing Predictive Ability of Models ..................................................... 36
Finding the right Tree Size ......................................................................... 37
Pruning: Cost Complexity Pruning.............................................................. 37
Comparing Trees (example) ....................................................................... 38
Trees: Useful as a variable selection tool ................................................... 39
Disadvantages of tree models.................................................................... 40
CART – How to in R .................................................................................... 40
CHAID – How to in R .................................................................................. 42
Entropy (C5.0) – How to in R ...................................................................... 42
Ensemble Learning..................................................................................... 42
, MADS MADLAD |6
Popular Ensemble Methods – Bagging, Boosting & Random Forest........... 43
Bagging: Bootstrap AGGregatING .............................................................. 43
Boosting..................................................................................................... 44
Bagging vs. Boosting .................................................................................. 46
Boosting – How to in R............................................................................... 46
Bagging – How to in R ................................................................................ 47
Pros & Cons: Log-regression vs. Trees vs. Bagging/Boosting ...................... 47
Week 3............................................................................................................. 48
Lecture 3: Random forests, Support Vector Machines, & Artificial Neural
Networks ...................................................................................................... 48
Random Forest .......................................................................................... 48
Support Vector Machines (SVM) ................................................................ 50
o Gaussian Radial Basis Function (RBF) ................................................... 54
Artificial Neural Networks .......................................................................... 54
Week 4............................................................................................................. 59
Lecture 4: Regularization .............................................................................. 59
Regularization ............................................................................................ 59
Linear Regression – Least Squares Regression (OLS) .................................. 59
Regularization technique 1: Forward Stepwise Selection ........................... 63
Regularization Technique 2: Ridge regression............................................ 67
Regularization Technique 3: Lasso regression ............................................ 68
Regularization Technique 4: Elastic-net regression .................................... 68
How to in R – Ridge, Lasso and Elastic-net regression ................................ 69
Hints on Assignment 2: .............................................................................. 73
Week 5............................................................................................................. 74
Lecture 5: Multi-armed Bandits .................................................................... 74
What is a multi-armed bandit problem? .................................................... 74
Epsilon Greedy Algorithms......................................................................... 77
Upper Confidence Bound algorithms (UCB) ............................................... 81
Thompson sampling algorithm .................................................................. 83
, MADS MADLAD |7
Bandits with Expert Advice ........................................................................ 85
Week 6............................................................................................................. 88
Lecture 6: Trustworthy AI ............................................................................. 88
What is trustworthy AI? ............................................................................. 88
Morality ..................................................................................................... 89
Incorporating Ethics into Marketing Decisions ........................................... 91
3 Stages in the ML flow prone to bias ........................................................ 92
Privacy ....................................................................................................... 93
2 Important laws in EU and USA on Privacy (GDPR & CCPA) ...................... 94
Week 7............................................................................................................. 97
Lecture 7: Causality and other ML issues ...................................................... 97
Churn probability vs. Change in churn ....................................................... 97
Limitations of correlation-based techniques .............................................. 97
Causality or Correlation (Criteria) .............................................................. 98
Uplift modeling .......................................................................................... 99
Extensions on non-binary outcomes ........................................................ 102
Predictive validity measures (PVM) ......................................................... 103
Example Exam 2021-22 .................................................................................. 106
, MADS MADLAD |8
Week 1
Lecture 1: Introduction to Machine Learning
Data Science Process
- Defining business problem (1)
o Ask questions to discover the real problem
▪ Management dilemma, questions
▪ Research questions
- Design the Research (2)
o Formulate hypotheses
o Literature research
o Define Constructs
- Data Collection & Preparation (3)
o Extracting data from sources
o Data Cleaning
o Data transformation (e.g., new variables)
- Explorative Analysis (4)
o Correlations, statistical tests, histograms, etc.
- Modelling (5)
o Specification (e.g., type and structure)
o Estimation
o Validation
o Interpretation
- Implementation (6)
o Communicating the results to stakeholders
o Data-driven storyline & visualization
, MADS MADLAD |9
- Monitoring (7)
o Monitoring the model’s performance
Criteria for a good model
- Simple
- Evolutionary
o Starting simple but building it up
- Complete
o As complete and simple as possible
- Adaptive
- Robust
o Able to use it in different circumstances
(e.g. during inflation, COVID, etc.)
What is (Machine) Learning?
Machine learning is concerned with computer programs that automatically
improve their performance through experience.
- Branch of AI and CS, which focuses on use of data and algorithms to
imitate the way that humans learn.
, M A D S M A D L A D | 10
3 Types of ML Models
- Supervised: uses a training set, including both input and correct (e.g.
labeled) output, to teach models to yield the desired output.
o Input + Annotations -> Model -> Prediction
o Used for: classificaition (sorting items into categories), regressions
- Unsupervised: Identifies patterns in data sets containing data points
that are neither classified nor labeled.
- Reinforcement: enforces models (gives feedback or corrections) to learn
how to make predictions.
- Visual Examples of the 3 Types:
The benefits of buying summaries with Stuvia:
Guaranteed quality through customer reviews
Stuvia customers have reviewed more than 700,000 summaries. This how you know that you are buying the best documents.
Quick and easy check-out
You can quickly pay through credit card or Stuvia-credit for the summaries. There is no membership needed.
Focus on what matters
Your fellow students write the study notes themselves, which is why the documents are always reliable and up-to-date. This ensures you quickly get to the core!
Frequently asked questions
What do I get when I buy this document?
You get a PDF, available immediately after your purchase. The purchased document is accessible anytime, anywhere and indefinitely through your profile.
Satisfaction guarantee: how does it work?
Our satisfaction guarantee ensures that you always find a study document that suits you well. You fill out a form, and our customer service team takes care of the rest.
Who am I buying these notes from?
Stuvia is a marketplace, so you are not buying this document from us, but from seller madsmadlad. Stuvia facilitates payment to the seller.
Will I be stuck with a subscription?
No, you only buy these notes for $16.28. You're not tied to anything after your purchase.
