Important: The focus of this course is on math - specifically, data-analysis concepts and methods - not on Excel for its own sake. We use Excel to do our calculations, and all math formulas are given as Excel Spreadsheets, but we do not attempt to cover Excel Macros, Visual Basic, Pivot Tables, or other intermediate-to-advanced Excel functionality.
This course will prepare you to design and implement realistic predictive models based on data. In the Final Project (module 6) you will assume the role of a business data analyst for a bank, and develop two different predictive models to determine which applicants for credit cards should be accepted and which rejected. Your first model will focus on minimizing default risk, and your second on maximizing bank profits. The two models should demonstrate to you in a practical, hands-on way the idea that your choice of business metric drives your choice of an optimal model.
The second big idea this course seeks to demonstrate is that your data-analysis results cannot and should not aim to eliminate all uncertainty. Your role as a data-analyst is to reduce uncertainty for decision-makers by a financially valuable increment, while quantifying how much uncertainty remains. You will learn to calculate and apply to real-world examples the most important uncertainty measures used in business, including classification error rates, entropy of information, and confidence intervals for linear regression.
All the data you need is provided within the course, all assignments are designed to be done in MS Excel, and you will learn enough Excel to complete all assignments. The course will give you enough practice with Excel to become fluent in its most commonly used business functions, and you’ll be ready to learn any other Excel functionality you might need in the future (module 1).
The course does not cover Visual Basic or Pivot Tables and you will not need them to complete the assignments. All advanced concepts are demonstrated in individual Excel spreadsheet templates that you can use to answer relevant questions. You will emerge with substantial vocabulary and practical knowledge of how to apply business data analysis methods based on binary classification (module 2), information theory and entropy measures (module 3), and linear regression (module 4 and 5), all using no software tools more complex than Excel.
Overview
Syllabus
- About This Course
- This course will prepare you to design and implement realistic predictive models based on data. In the Final Project (module 6) you will assume the role of a business data analyst for a bank, and develop two different predictive models to determine which applicants for credit cards should be accepted and which rejected. Your first model will focus on minimizing default risk, and your second on maximizing bank profits. The two models should demonstrate to you in a practical, hands-on way the idea that your choice of business metric drives your choice of an optimal model.The second big idea this course seeks to demonstrate is that your data-analysis results cannot and should not aim to eliminate all uncertainty. Your role as a data-analyst is to reduce uncertainty for decision-makers by a financially valuable increment, while quantifying how much uncertainty remains. You will learn to calculate and apply to real-world examples the most important uncertainty measures used in business, including classification error rates, entropy of information, and confidence intervals for linear regression. All the data you need is provided within the course, and all assignments are designed to be done in MS Excel. The course will give you enough practice with Excel to become fluent in its most commonly used business functions, and you’ll be ready to learn any other Excel functionality you might need in future (module 1). The course does not cover Visual Basic or Pivot Tables and you will not need them to complete the assignments. All advanced concepts are demonstrated in individual Excel spreadsheet templates that you can use to answer relevant questions. You will emerge with substantial vocabulary and practical knowledge of how to apply business data analysis methods based on binary classification (module 2), information theory and entropy measures (module 3), and linear regression (module 4 and 5), all using no software tools more complex than Excel.
- Excel Essentials for Beginners
- In this module, will explore the essential Excel skills to address typical business situations you may encounter in the future. The Excel vocabulary and functions taught throughout this module make it possible for you to understand the additional explanatory Excel spreadsheets that accompany later videos in this course.
- Binary Classification
- Separating collections into two categories, such as “buy this stock, don’t but that stock” or “target this customer with a special offer, but not that one” is the ultimate goal of most business data-analysis projects. There is a specialized vocabulary of measures for comparing and optimizing the performance of the algorithms used to classify collections into two groups. You will learn how and why to apply these different metrics, including how to calculate the all-important AUC: the area under the Receiver Operating Characteristic (ROC) Curve.
- Information Measures
- In this module, you will learn how to calculate and apply the vitally useful uncertainty metric known as “entropy.” In contrast to the more familiar “probability” that represents the uncertainty that a single outcome will occur, “entropy” quantifies the aggregate uncertainty of all possible outcomes. The entropy measure provides the framework for accountability in data-analytic work. Entropy gives you the power to quantify the uncertainty of future outcomes relevant to your business twice: using the best-available estimates before you begin a project, and then again after you have built a predictive model. The difference between the two measures is the Information Gain contributed by your work.
- Linear Regression
- The Linear Correlation measure is a much richer metric for evaluating associations than is commonly realized. You can use it to quantify how much a linear model reduces uncertainty. When used to forecast future outcomes, it can be converted into a “point estimate” plus a “confidence interval,” or converted into an information gain measure. You will develop a fluent knowledge of these concepts and the many valuable uses to which linear regression is put in business data analysis. This module also teaches how to use the Central Limit Theorem (CLT) to solve practical problems. The two topics are closely related because regression and the CLT both make use of a special family of probability distributions called “Gaussians.” You will learn everything you need to know to work with Gaussians in these and other contexts.
- Additional Skills for Model Building
- This module gives you additional valuable concepts and skills related to building high-quality models. As you know, a “model” is a description of a process applied to available data (inputs) that produces an estimate of a future and as yet unknown outcome as output. Very often, models for outputs take the form of a probability distribution. This module covers how to estimate probability distributions from data (a “probability histogram”), and how to describe and generate the most useful probability distributions used by data scientists. It also covers in detail how to develop a binary classification model with parameters optimized to maximize the AUC, and how to apply linear regression models when your input consists of multiple types of data for each event. The module concludes with an explanation of “over-fitting” which is the main reason that apparently good predictive models often fail in real life business settings. We conclude with some tips for how you can avoid over-fitting in you own predictive model for the final project – and in real life.
- Final Course Project
- The final course project is a comprehensive assessment covering all of the course material, and consists of four quizzes and a peer review assignment. For quiz one and quiz two, there are learning points that explain components of the quiz. These learning points will unlock only after you complete the quiz with a passing grade. Before you start, please read through the final project instructions. From past student experience, the final project which includes all the quizzes and peer assessment, takes anywhere from 10-12 hours.
Taught by
Jana Schaich Borg and Daniel Egger
Tags
Related Courses
Related articles
Reviews
1.9 rating, based on 27 Class Central reviews
4.2 rating at Coursera based on 3919 ratings
-
FYI: I paid for this course. I was really enjoying the course (second course in the series)up until week 1 and really looking forward to the simple and easy way of learning from week 1 and course 1 of this series. But just in week 2, things starte…
-
Don't waste your time. I finished the course (waiting on the peer review grade) and did learn some things. But the learning was from the discussion forum and a lot of trial and error. The only Excel you will do is in the assignments. The lectures ar…
-
This course is NOT the course to take if you want to learn Excel or to build analytical models in Excel. Instead it's a course that seems to be presenting fairly sophisticated analytical techniques using already-built Excel models. The lectures we…
-
The class focused on how certain statistical models are implemented in Excel - in theory. Although no math backgound was required, don't even think about taking this class unless you are an Excel power user with integral and differential Calculus, statistics I and II, and machine learning under your belt otherwise you will be totally lost.
-
DO NOT WASTE YOUR TIME WITH THIS COURSE.
I concur with Brian O's assessment. He is 100% right with his comments about what is needed. I have all of that and more (S.T.E.M. courses out my ears, grad and undergrad) and have successfully completed six other quantitative courses from Coursera. It is sloppy and unprofessional beyond belief. Terms are not defined, quizzes are confusing and you will spend most of your time trying to figure out what is being asked. It's not worth your time, let alone the $79 for a cert. In addition, most of what he does in Excel is much better done in R or JMP or any of the other packages out there.
-
The course video lectures are of no use, if you want to complete this course, you gotta work a lot by yourself. Discussion Forum may help you. Better you spend your time learning same concepts from anywhere else. Literally, every concept taught has a better explained video on youtube.
-
The course content had very little to do with Excel. More like Excel is just a briefly mentioned tool, rather than the main training environment of the course. Moreover, all the concepts taught are very loosely related to each other. At points it feel like the concepts are just there for the sake of making the course looking high-level and complicated. But at the core of it, it feels like there's little to none coherency in all the lectures, assignments and problems put forward.
-
Frankly the course left me feeling disappointed - the concepts therein are truly important and interesting, and Mr. Egger is an enthusiastic, likeable and very knowledgeable teacher. BUT This is NOT an introductory course. This is NOT a course on…
-
I concur with all other negative comments. I had a high expectation and was very excited to take this course, but found out this course has very little to do with Excel. It is mainly statistics. Worse than that, the video lectures are way too brie…
-
The course "Mastering Data Analysis in Excel" provided a comprehensive overview of Excel's data analysis capabilities. It covered fundamental concepts such as data cleaning, manipulation, pivot tables, and advanced functions effectively. The structured learning approach and practical exercises were beneficial for understanding complex topics. However, it could have delved deeper into certain areas and offered more updated content. Overall, it significantly improved my proficiency in Excel for data analysis, but some aspects could have been more in-depth and current.
-
I'm currently struggling through this course. Having completed 4 weeks with more hours spend than advertised, I can only say that to pass the exams you just need to write down each answer and resit the exam for the incorrect answers until you pass the test. The video lessons do not give you the tools or the knowledge to pass the tests. Prior advance math and statistics knowledge is assumed by the professor and it definitely does not cater to beginners, as advertised.
Based on comments above I started working on the final assignment and am feeling utterly demotivated as the prior video lessons do not prepare you enough for the final assignment...BEWARE! -
I had such high expectations for this course, and I am absolutely crushed by how far it has fallen from them. I'm not learning very much and am only passing the quizzes by relying on the hints provided after failing them the first time. Even after I manage to pass a quiz, I do not have a thorough understanding of the material--certainly nothing I would actually be able to use in a job in the industry.
I'm becoming very concerned that I paid for this course and the specialization. Beware. -
I paid for this course, I have engineering background and work in IT so I had already learnt some of the math and statistics needed in this course, but forgotten after 12 years. The course videos are very poorly designed and I had to refer a lot elsewhere like on youtube and Khan academy, which in spite of being a free website was so much better. I ended up making a donation to KA and would recommend taking their High School Probability and Statistics course before you take this one.
-
I enjoyed Week 1 of this course (and have completed the previous course in the specialization), but like many other reviewers, am finding the material in Week 2 way over my head and poorly explained. This is not an "introductory" course by any means - if you do not have some prior knowledge of the mathematical and statistical concepts covered here you will flounder. I'm spending half my time looking up things elsewhere to get clarification (for free) that I'm not getting here in a course I'm paying for. Not sure I'll be sticking with this one.
-
Please, save yourself 6 weeks of your precious time! Material is really poor and final project is disconnected from weekly lessons. Duke University Board must have a look at this course and take it out from the catalog until material is improved
-
Xiaotao GuoIf you want to learn some skills in excel, i don't think it worth learning because from the second week i'm keep learning some math knowledge and they're sometimes difficult to understand. -
I dropped into the 6th week. I totally concur with the other negative comments. I found the errors to be totally unacceptable. Disappointing because I really wanted to learn something.
BTW - I was going to rate it zero stars but it makes me place at least one star. -
It's a math course not an Excel course. It's difficult and the instructor's sloppy hand doodling/writing in the videos only made it more challenging to capture what was being taught.
-
This course talks little about excel. Instead, it spent a lot of time on statistics.
Do not take this course if you want to learn practical skills. -
This course is awesome. Set Clear Expectations. When you are designing an online discussion, take a moment to think about what you want the students to achieve.
