Business Analytics Course Overview

Business Analytics as a program of study at Haas

Haas analytics courses are deliberately coordinated in a layered fashion. All students are required to take Data and Decisions so as to achieve basic literacy in quantitative analysis. Students interested in understanding the landscape of business analytics concepts may select from one or more of MBA263, MBA217, and MBA240. The syllabi of these three courses are coordinated to maximize complementarities (and minimize redundancies) among methods and problem-domains while providing the next level of depth in quantitative, data-driven decision-making. Beyond the primary courses are a number of secondary, domain-specific courses. Each includes additional quantitative, analytics modules.

A student pursuing the Business Analytics program of study must take one of the three primary courses. They must then complete at least two secondary courses. The cumulative effect is to allow students to simultaneously develop proficiency in Business Analytics while pursuing a domain emphasis.

Marketing Analytics MBA/EWMBA 263 3-Unit

In this course, students will gain hands-on experience with data analytics for the purpose of learning about and marketing to customers. The goal is not to produce experts in statistics; the goal is to gain the competency to interact with and manage a data science team.

Details

Business Context

  • Customer acquisition, targeting and retention
  • Experimental design of products and promotions
  • Search Engine Optimization
  • Web analytics (marketing)

Concepts

  • Descriptive Models
  • Predictive Models and Inference
  • Unsupervised Machine Learning
  • Supervised Machine Learning

Algorithms

  • Segmentation and Clustering with RFM
  • Logistic regression
  • Neural Networks/Deep learning
  • Discrete Choice models and Full-factorial designs

Tech Platform

  • Jupyter
  • Notebook +
  • Python-kernel

Business Context

  • Customer acquisition, targeting and retention
  • Experimental design of products and promotions
  • Search Engine Optimization
  • Web analytics (marketing)

Concepts

  • Descriptive Models
  • Predictive Models and Inference
  • Unsupervised Machine Learning
  • Supervised Machine Learning

Algorithms

  • Segmentation and Clustering with RFM
  • Logistic regression
  • Neural Networks/Deep learning
  • Discrete Choice models and Full-factorial designs

Tech Platform

  • Jupyter
  • Notebook +
  • Python-kernel

Big Data & Better Decisions MBA/EWMBA 217 3-Unit

Details

Business Context

  • Health policy
  • Financial risk management
  • Impact analysis (economic analysis and policy)

Concepts

  • Descriptive Models
  • Predictive Models and Inference
  • Supervised Machine Learning

Algorithms

  • Linear Regression
  • Logistic Regression
  • High-dimensional linear models (RIDGE, LASSO)
  • Tree models and random forests

Tech Platform

  • Jupyter Notebook w/ R-kernel

Business Context

  • Health policy
  • Financial risk management
  • Impact analysis (economic analysis and policy)

Concepts

  • Descriptive Models
  • Predictive Models and Inference
  • Supervised Machine Learning

Algorithms

  • Linear Regression
  • Logistic Regression
  • High-dimensional linear models (RIDGE, LASSO)
  • Tree models and random forests

Tech Platform

  • Jupyter Notebook w/ R-kernel

Decision Models MBA/EWMBA 240 2-Unit

This course aims to enhance your ability to understand and structure complicated decision problems, analyze complex trade-offs efficiently and to appreciate the risks associated with each alternative. The course will equip you with state-of-the-art decision support tools that allow you to evaluate different courses of action.

Details

Business Context

  • Revenue Management
  • Financial Planning
  • Resource Allocation (operations, marketing, finance and accounting)

Concepts

  • Prescriptive Models
  • Constrained Optimization
  • Decision Analysis
  • Simulation and Optimization

Algorithms

  • Linear Programming
  • Mixed Integer Linear Programming
  • Bayesian Analysis and Decision Trees
  • Monte Carlo Simulation

Tech Platform

  • Excel
  • Analytic Solver Plug-In

Business Context

  • Revenue Management
  • Financial Planning
  • Resource Allocation (operations, marketing, finance and accounting)

Concepts

  • Prescriptive Models
  • Constrained Optimization
  • Decision Analysis
  • Simulation and Optimization

Algorithms

  • Linear Programming
  • Mixed Integer Linear Programming
  • Bayesian Analysis and Decision Trees
  • Monte Carlo Simulation

Tech Platform

  • Excel
  • Analytic Solver Plug-In

Descriptive & PredictiveData Mining MBA/EWMBA 247-11 1-unit

The primary goals of this course are twofold: to make all students intelligent “consumers” of data mining performed by experts, and to motivate many students to be “suppliers” of data mining to colleagues at work.

Details

Business Context

  • Financial Reporting
  • Resource Allocation
  • Workplace analytics
  • Web analytics
  • Electoral politics and voter targeting

Concepts

  • Descriptive Models
  • Predictive Models and Inference
  • Descriptive Statistics
  • Unsupervised Machine Learning
  • Supervised Machine Learning

Algorithms

  • k-Means clustering
  • Association Rules
  • k-NN classification
  • rule-based decision tree classification

Tech Platform

  • Excel
  • Analytic Solver Plug-In

Business Context

  • Financial Reporting
  • Resource Allocation
  • Workplace analytics
  • Web analytics
  • Electoral politics and voter targeting

Concepts

  • Descriptive Models
  • Predictive Models and Inference
  • Descriptive Statistics
  • Unsupervised Machine Learning
  • Supervised Machine Learning

Algorithms

  • k-Means clustering
  • Association Rules
  • k-NN classification
  • rule-based decision tree classification

Tech Platform

  • Excel
  • Analytic Solver Plug-In

Data Science & Data Strategy MBA/EWMBA296-8B 2-unit

The objective of this course is to convey the role of data analytics in decision-making. We focus on the role of managers as both consumers and producers of information, illustrating how finding and/or developing the right data and applying appropriate statistical methods can help solve problems in business.

Details

Business Context

  • Business strategy
  • Problems in marketing, operations, workforce management, and finance through the lens of data and machine intelligence.

Concepts & Algorithms

  • High-level survey of several different methods in unsupervised and supervised machine learning; an emphasis on the business context and exploiting firm data for strategic advantage.

Tech Platform

  • BigML Proprietary SaaS Application Excel

Business Context

  • Business strategy
  • Problems in marketing, operations, workforce management, and finance through the lens of data and machine intelligence.

Concepts & Algorithms

  • High-level survey of several different methods in unsupervised and supervised machine learning; an emphasis on the business context and exploiting firm data for strategic advantage.

Tech Platform

  • BigML Proprietary SaaS Application Excel
Business Problem Context
You came to the Haas School of Business in order to learn to become a leader, not to become a data scientist.  Haas courses therefore are largely designed to introduce principles of data analytics in the context of business and leadership.  However, this in no way is meant to imply that certain concepts or algorithms only apply to one type of context.  We recognize that requirements limit the number of electives a student may take.  The business analytics curriculum is coordinated to enable a student to learn basic concepts (e.g. supervised v. unsupervised learning, evaluating the performance of a categorical classifier, experimental design) in one of several different courses.   At the same time, students seeking greater depth can elect additional courses and revisit the same higher-level concepts but with different concrete algorithms and applied to different types of business problems.

Concepts & Algorithms
The different courses introduce the concepts and algorithms of business analytics in a particular domain context (e.g. marketing, operations, health care). However, this in no way is meant to imply that certain concepts or algorithms only apply to one type of context. The space of “supervised machine learning,” for example, includes any number of algorithms. Haas courses are coordinated so that a student may take a single class and learn multiple concepts by applying particular algorithms to one type of business problems. We recognize that requirements limit the number of electives a student may take. To optimize for student accessibility to analytics concepts, complementary algorithms are taught in courses that frame a different set of business problems. Moreover, as a world-class University at the forefront of data science, you have opportunities to dive deeper. You may register for courses in Statistics, Engineering, and Mathematics if your objective is to learn the core principles not only of algorithms but also of data manipulation, storage, and distribution. Haas courses focus on the application of analytics to business decision-making.

Technology Platform
In addition to Excel, Haas, is migrating to a common technology platform for business analytics. The Jupyter Notebook is a technology platform emerging as a standard in the data science community. Although open source, Jupyter was largely invented and currently developed and maintained at UC Berkeley. Jupyter is one implementation of the Notebook paradigm. R-studio, a popular interface for R now has a format that mimics the notebook paradigm as does Matlab (these are other software tools for algorithmic data manipulation which you may have heard of). Haas is creating a Jupyter environment in a software-as-a-service platform called JupyterHub, which you will access via your Web browser. Depending upon the course, you will use R or Python. No one tool strictly dominates the other; they stem from different traditions. As a general purpose programming language, Python is more common in the engineering-based courses. R is more common in advanced statistics courses. At UC Berkeley, both the Statistics and EECS (Electrical Engineering and Computer Science) departments have converged on Python as the base platform for all introductory courses and teach using Jupyter notebooks.