DS4B 201-R – Data Science For Business With R
Price: $499
Archive: https://archive.is/X0WL7
Solve a real-world churn problem with H2O AutoML (automated machine learning) & LIME black-box model explanations using R
Please note that the Shiny Web Application is built in DS4B 301-R: Building A Shiny Web Application (Coming Soon!)
DS4B 201-R teaches you the tools and frameworks for ROI-driven data science using the R-programming language.
Over the course of 10-weeks you’ll dive in-depth into an Employee Attrition (Churn) problem, learning & applying a systematic process, cutting-edge tools, and R code.
At the end of the course, you’ll be able to confidently apply data science within a business.
The difference with the DS4B 201-R program: You get results!
Week 1: Getting Started
You begin with the problem overview and tool introduction covering how employee churn effects the organization, our toolbox to combat the problem, and code setup.
We introduce the Business Science Problem Framework, which is our step-by-step roadmap for data science project success.
The BSPF is used as guide as you progress through each chapter in the course.
Week 2: Business Understanding
You progress into sizing the problem.
You develop skills with dplyr and ggplot2, critical to exploring data. You are introduced to a new metaprogramming language called Tidy Eval for programming with dplyr.
You use Tidy Eval for the attrition code workflow, building a customizable plotting function to show executives which departments and job roles are costing the organization the most due to attrition.
Week 3: Data Understanding
The goal is to not waste time. You’ll learn two critical packages for exploring data and uncovering insights quickly.
First, you’ll investigate data by data type using the skimr package. You investigate continuous (numeric) and categorical (factor) data.
Next, you’ll investigate data relationships visually using GGally. You uncover key relationships between the target variable (attrition) and the features (e.g. tenure, pay, etc).
Week 4: Data Preparation
Next, you prepare the data for both humans and machines with the goal of making sure you have good features prior to moving into modeling. Again, the goal is to not waste time until we have fully understood the problem and have good features.
First, you use the tidyverse packages to wrangle data into a format that is readable by humans, creating a “human readable” processing pipeline.
Next, you use the recipes package to create a “machine readable” processing pipeline that is used to create a pre-modeling correlation analysis visualization.
The correlation analysis confirms we have good features and can proceed to modeling.
Weeks 5 & 6: H2O Modeling & Performance Analysis
Next, you learn H2O, a high performance modeling package. You spend two chapters with H2O.
In Chapter 4 (modeling), you learn the primary H2O functions for automated machine learning. You generate models including:
- Generalized Linear Models (GLM)
- Gradient Boosted Machines (GBM)
- Random Forest (RF)
- Deep Learning (DL)
- Stacked Ensembles.
You create a visualization that examines the 30+ models you build.
In Chapter 5 (performance), you go in-depth into performance analysis. You learn about ROC Plot, Precision vs Recall, Gain & Lift Plots (which are for executive communication). You build the “ultimate model performance dashboard”.
Week 7: Explaining Black-Box Models
“The business won’t care how high your AUC is if you can’t explain your Machine Learning models. Explain those models.”
-Matt Dancho, Founder of Business Science
Now, you learn about LIME and how to perform local machine learning interpretability to explain complex models, showing which features contribute to attrition on a localized, employee level.
You’ll also have a cool challenge where you recreate the plots with a business-ready theme .
Weeks 8 & 9: Expected Value, Threshold Optimization, & Sensitivity Analysis
Now it’s time to link Machine Learning to Expected Financial Performance. You spend two chapters with on expected value, threshold optimization, and sensitivity analysis.
We start with a basic case of making a “No Overtime” policy change. We then go through Expected Value Framework, a tool that enables targeting high-risk churners and accounts costs associated with false negatives / false positives.
We then teach how to optimize the threshold using purrr for iteration to maximize expected savings of a targeted policy. We then teach you Sensitivity Analysis again using purrr to show a heatmap that covers confidence ranges that you can explain to executives.
Week 10: Recommendation Algorithm Development
“To make progress, you need to make good decisions. Good decisions are systematic and data-driven.”
-Matt Dancho, Founder of Business Science
This is the culmination of your hard work. It’s time to apply critical thinking skills by developing a data-driven recommendation algorithm from scratch.
You will follow a 3-Step Process that shows you how to build a recommendation algorithm for any business problem.
We Didn’t Stop There. You Also Get…
Bonus #1: Market Basket Analysis ($995 Value)
As an added bonus, you get a detailed Market Basket Analysis using the recommenderlab R package. You’ll learn how to generate product recommendations using:
- Collaborative Filtering
- Association Rules
- Item Popularity
- Content-Based Filtering
- Hybrid Models
Bonus #2: Private Slack Community Channel ($1,995 Value)
We have an exclusive slack channel for students of DS4B 201-R. This is an amazingly useful resource ! Students use it to connect with peers, ask questions, and share data science resources.
Did we mention that Erin LeDell, Chief Machine Learning Scientist at H2O.ai and creator of the H2O AutoML algorithm is in our Private Slack Channel?
No other program has this level of support. Period.
Bonus #3: Instructor Access
Our instructors are experts in data science and machine learning. You have exclusive access to instructors through the Private Slack Channel, email, and lecture forums. This is a great way to ask questions, get mentored, and learn from an expert.
You can connect with Matt! Shoot him an email. He’ll respond quickly.
Summary Of Everything Included
- 10-Week Data Science For Business With R Program : $5,000 value (compared to 5-Day On-Site Workshop)
- Business Science Problem Framework Training
- Sizing Problem, Data Exploration, Preprocessing, & Pre-modeling Correlation Analysis Training
- Machine Learning Training: H2O & LIME
- Expected Value Training: Threshold Optimization & Sensitivity Analysis
- Recommendation Algorithm Development Training: 3-Step Process
- Bonus #1: Market Basket Analysis ML Tutorial: $995 Value
- Bonus #2: Private Slack Community Channel: $1,995 Value
- Bonus #3: Instructor Access: Priceless 🙂
$499.00
$99.00
Reviews
There are no reviews yet.