As you work through the hands-on modules, you will gain meaningful business
insights from the data and example cases derived from a broad sampling of
industries.
Module 1:
Probabilistic Decision Making
We’ll introduce the foundational concepts behind data science and analytics before
exploring the fundamentals of data.
- Compare categorical vs. numerical data.
- Explore the basic ways that data reveal information.
- Learn from a healthcare example: HMO membership and doctor visits using
aggregated data.
- Become acquainted with Jupyter Notebook, Python, and Panda.
Module 2:
Creating Sample Data
Learn the definitions of key survey terms as well as methods that use sampling to
analyze the pros and cons of business decisions through the exploration of
sampling, type I and type II errors, and control limits.
- Learn to define types of data samples, sampling variation, and quality.
- Identify and define foundational sampling concepts.
- Identify and mitigate bias when sampling data.
- Evaluate examples that illustrate joint, marginal, and conditional probability:
Comcast, Google, and Nextag.
Module 3:
Testing Hypotheses
Making data-driven business decisions relies on well-articulated hypotheses that
lend themselves to statistical tests. We’ll cover the foundations of this approach,
including statistical comparisons, confidence intervals, and margins of error.
- Identify the basic tenets of experimentation.
- Identify and discriminate between one-sided and two-sided statistical tests.
- Complete problem sets using the 4M model (Motivation, Method, Mechanics,
and Message).
- Analyze an industry example: 24 Hour Fitness tests a new proprietary
diet—testing between control and treatment groups.
Module 4:
Extrapolating Information from Sample Data
We’ll explore the most common linear and curved patterns and understand different
ways to fit data to linear models. A central application will be understanding market
demand, price setting, and elasticities.
- Identify conditions for using and interpreting linear and curved patterns.
- Examine curved (non-linear) patterns as applied to vehicle weight and fuel
efficiency.
- Complete problem sets using the 4M model for credit cards, crime, and
housing prices in Philadelphia.
Module 5:
Basic Regression Models
Simple regression analyses are at the heart of more elaborate data-driven business
decision making. We’ll focus on understanding how these models are used, the
assumptions that make their use valid, and how to leverage these models to make
better business decisions.
- Define and apply the simple regression model and identify conditions for its
use.
- Apply and interpret prediction intervals.
- Identify three major problems that affect regression models: changing variation
in data, outliers, and dependence among observations.
- Practice with a retail example: use regression modeling to determine the
location of a franchise outlet.
Module 6:
Advanced Regression Models
Build on the basics to define the multiple regression model and explore different use
cases.
- Discriminate between marginal and partial slopes.
- Articulate inference in the multiple regression model.
- Summarize the process of fitting and building a multiple regression model.
- Learn from a financial example: build a multiple regression model to explain
the returns on Sony’s stock.
- Practice with a human resources example: analyze salary data using MRM to
identify gender imbalances.
Module 7:
Forecasting and Machine Learning
We’ll demystify machine learning by mastering the fundamentals and studying
different applications.
- Discriminate between supervised, semi-supervised, and unsupervised learning.
- Examine machine learning approaches, including the “bag-of-words” method
for supervised learning.
- Practice forecasting by using time series regressions.
- Explore a cybersecurity example: machine learning for spam detection.
Module 8:
A/B Testing & Building Effective Data Science Teams
With the fundamentals and some of the most common tools under our belts, we’ll
dive deep into the competencies that define effective data science teams and show
you how to build a data-driven culture in your organization. We will stress common
pitfalls and strategies to work effectively with data scientists.
- Review the requirements for building effective data science teams.
- Continue the exploration of building a data-driven culture.
- Evaluate an advertising example: Rocket Fuel’s conversion rate, benefit, ROI, opportunity cost, and A/B testing.
Module 1:
Probabilistic Decision Making
We’ll introduce the foundational concepts behind data science and analytics before
exploring the fundamentals of data.
- Compare categorical vs. numerical data.
- Explore the basic ways that data reveal information.
- Learn from a healthcare example: HMO membership and doctor visits using
aggregated data.
- Become acquainted with Jupyter Notebook, Python, and Panda.
Module 5:
Basic Regression Models
Simple regression analyses are at the heart of more elaborate data-driven business
decision making. We’ll focus on understanding how these models are used, the
assumptions that make their use valid, and how to leverage these models to make
better business decisions.
- Define and apply the simple regression model and identify conditions for its
use.
- Apply and interpret prediction intervals.
- Identify three major problems that affect regression models: changing variation
in data, outliers, and dependence among observations.
- Practice with a retail example: use regression modeling to determine the
location of a franchise outlet.
Module 2:
Creating Sample Data
Learn the definitions of key survey terms as well as methods that use sampling to
analyze the pros and cons of business decisions through the exploration of
sampling, type I and type II errors, and control limits.
- Learn to define types of data samples, sampling variation, and quality.
- Identify and define foundational sampling concepts.
- Identify and mitigate bias when sampling data.
- Evaluate examples that illustrate joint, marginal, and conditional probability:
Comcast, Google, and Nextag.
Module 6:
Advanced Regression Models
Build on the basics to define the multiple regression model and explore different use
cases.
- Discriminate between marginal and partial slopes.
- Articulate inference in the multiple regression model.
- Summarize the process of fitting and building a multiple regression model.
- Learn from a financial example: build a multiple regression model to explain
the returns on Sony’s stock.
- Practice with a human resources example: analyze salary data using MRM to
identify gender imbalances.
Module 3:
Testing Hypotheses
Making data-driven business decisions relies on well-articulated hypotheses that
lend themselves to statistical tests. We’ll cover the foundations of this approach,
including statistical comparisons, confidence intervals, and margins of error.
- Identify the basic tenets of experimentation.
- Identify and discriminate between one-sided and two-sided statistical tests.
- Complete problem sets using the 4M model (Motivation, Method, Mechanics,
and Message).
- Analyze an industry example: 24 Hour Fitness tests a new proprietary
diet—testing between control and treatment groups.
Module 7:
Forecasting and Machine Learning
We’ll demystify machine learning by mastering the fundamentals and studying
different applications.
- Discriminate between supervised, semi-supervised, and unsupervised learning.
- Examine machine learning approaches, including the “bag-of-words” method
for supervised learning.
- Practice forecasting by using time series regressions.
- Explore a cybersecurity example: machine learning for spam detection.
Module 4:
Extrapolating Information from Sample Data
We’ll explore the most common linear and curved patterns and understand different
ways to fit data to linear models. A central application will be understanding market
demand, price setting, and elasticities.
- Identify conditions for using and interpreting linear and curved patterns.
- Examine curved (non-linear) patterns as applied to vehicle weight and fuel
efficiency.
- Complete problem sets using the 4M model for credit cards, crime, and
housing prices in Philadelphia.
Module 8:
A/B Testing & Building Effective Data Science Teams
With the fundamentals and some of the most common tools under our belts, we’ll
dive deep into the competencies that define effective data science teams and show
you how to build a data-driven culture in your organization. We will stress common
pitfalls and strategies to work effectively with data scientists.
- Review the requirements for building effective data science teams.
- Continue the exploration of building a data-driven culture.
- Evaluate an advertising example: Rocket Fuel’s conversion rate, benefit, ROI, opportunity cost, and A/B testing.
Note: In order to help you explore some of the hands-on techniques that lead directly to making better data-driven decisions, there will be two weeklong learning labs that provide an opportunity to dig deeper into the data. This extends the program to a total of 10 weeks.
