A Business Analyst’s Introduction to Business Analytics
Intro to Bayesian Business Analytics in the R Eco-System (Featuring R, Rstudio, the tidyverse, graphical models, Bayesian inference, causact, and greta’s TensorFlow interface from R.)
Adam Fleischhacker
2021-08-07
Chapter 1 Welcome
Figure 1.1: In this book, you will become the business analyst who easily travels between the real-world of business and the theoretical world of mathematics. You will translate real-world scenarios into both mathematical and computational representations that yield actionable insight. You will then take that insight back to the real-world to persuade stakeholders to alter and improve their real-world decisions.
This textbook goes farther than just teaching you to make computational models using software or mathematical models using statistics. It teaches you how to align computational and mathematical models with real-world scenarios; empowering you to communicate with and leverage the expertise of business stakeholders while using modern software stacks and statistical workflows. In this book, you do not learn business analytics to make models; you learn business analytics to add tangible value in the real-world.
Figure 1.2: Buy a beautifully printed in-color version of “A Business Analyst’s Guide to Business Analytics” on Amazon: http://www.amazon.com/dp/B08DBYPRD2.
If you want to learn business analytics to unlock actionable insight from within data and persuade stakeholders to follow your recommendations, then this is the book for you. Written by me, Dr. Adam Fleischhacker, award-winning professor, software designer, researcher, and industry-active analytics consultant. I wrote this guide to accelerate your journey mastering the data-driven business analyst workflow.
On your journey to becoming a world-class business analyst who combines data with business knowledge, here are some highlights of what you will encounter using this textbook:
- Lessons for learning a complete business analytics workflow using the R programming language including data manipulation, data visualization, modelling business problems with graphical models, translating graphical models into code, and presenting insights back to stakeholders.
- Content that is accessible to most analytics beginners. If you have taken a stats course, you will benefit from this book. The book assumes no prior knowledge of any software and introduces readers to the proper toolkit for business analytics including R, RStudio, and the tidyverse.
- A single interface to a complete analytics workflow within the R-ecosystem; there is no need to learn several programming languages.
- A non-intimidating and gentle approach to learning Bayesian inference and Bayesian data analysis.
- First textbook using
greta, an R interface toTensorFlowfor Bayesian inference, and thecausactpackage for visual model development. - Code to reproduce all results and almost all visualizations is included right in the text.
- An analytics perspective of a professor who wins teaching awards and has had a successful corporate career in analytics and software product management.
- All datasets in the book are freely and easily accessed.
- Cloud computing options freely available for those who are limited to internet browser access only.
1.1 Accompanying Videos
Videos that help the material come to life are available on my YouTube channel. The videos are supplements to the chapters and should be watched after reading and coding along with each chapter. Search for Adam Fleischhacker on YouTube or follow this link directly: https://www.youtube.com/playlist?list=PLassxuIVwGLPy-mtohX-NXrjD8fc9FBOc.
1.2 Online Notes for Professors Considering Adopting This Book
At its heart, this is a Bayesian business analytics textbook made feasible by recent advances in Bayesian computing.\(^{**}\) ** Most notably the use of better sampling techniques using adaptations of something known as Hamiltonian Markov Chain Monte Carlo (HMCMC). Using Bayesian inference is the provably best method of combining data with domain knowledge to extract interpretable and insightful results that lead us towards better outcomes. In my opinion, this is what students need to learn to be clear-thinking and capable business analysts.
To use some of the datasets and functions that accompany this book, readers will eventually need to install the causact R package and its dependencies (this installation process is covered in Chapter 15). Datasets and graph visualization do not require the dependencies and just require one to run this line:
install.packages("causact")However, to use advanced functionality this package should be installed with greta (an R package) and TensorFlow (a free and open-source software library). Properly installing causact, greta, and Tensorflow can be done following the instructions here: https://www.causact.com/install-tensorflow-greta-and-causact.html.
If you want to jump to causact package specifics, start here: https://www.causact.com/causact-quick-inference-with-generative-dags.html#causact-quick-inference-with-generative-dags.
Please note that this work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (https://creativecommons.org/licenses/by-nc-nd/4.0/).
To support this work send feedback/follow me via Twitter:
Follow @preposteriorand consider buying the printed version on Amazon. See it here: http://www.amazon.com/dp/B08DBYPRD2
A Business Analyst’s Introduction to Business Analytics by Adam Fleischhacker is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.