Analytics in the Real World

Order Details;

What is Business analytics ?


Course Rationale   This course provides an introduction to data presentation, handling and mathematical modeling using spreadsheets.  Managers use such models in support for effective decision making.  Traditionally Management Science and Statistics are the disciplines that focus on developing models for management scenarios.  Today the link between the techniques of management science and statistics and the disciplines of engineering, computer science, business and economics is growing rapidly.  Business Analytics is a course that emphasizes data management and modeling applications that are useful for managerial decision making in operations, marketing and finance.


Business Analytics will consist of four sections.  The class will begin with an introduction to spreadsheets and building basic spreadsheet models.  Practice handling large data sets using pivot tables and the application of data description tools will be addressed.  The second section will consist of optimization models including linear, integer and non-linear mathematical programming.  The third section will focus on using the tools built into MS Excel for modeling relationships between variables, for forecasting and for mining for patterns in data applied in business settings.  Simulation and Decision analysis will make up the fourth and final major topic of the course.  In all cases the student will practice modeling and solving problems that are faced by management.


A very broad set of business applications will be investigated during the course. The course begins with an introduction to basic spreadsheet models including breakeven analysis and time value of money analysis. Operations applications include production and workforce planning, purchasing (fixed charge), inventory and location models.  Finance applications include capital budgeting, portfolio optimization and options pricing models.  Advertising, pricing, segmentation analysis are examples of marketing applications to be covered.


In this course students will be required to model, solve and interpret the results of management problems that use quantitative techniques and tools. The widespread use of spreadsheet software in the workplace presents a compelling reason for utilizing this application for the majority of the quantitative analysis undertaken in the course.  The skills imparted through the use of spreadsheets will enable the students to be better equipped for modeling and solving quantitative problems in the future.


Course Description This course focuses on business analytics and mathematical modeling. Extending the skills obtained in the business statistics course, this class focuses on models for prescriptive and predictive analytics as well as structured decision making under uncertainty. Multiple regression modeling, business forecasting, Monte Carlo simulation, risk modeling applications will be covered, as well as optimization including linear, integer and non-linear programming. Decision analysis will make up the final major topic of the course. The course emphasizes applications that are useful for managerial decision making in operations, marketing and finance settings.


Learning Outcomes A student completing this course will be able to:

  • Describe a basic problem formulation and decision analysis process
  • Build well-structured and clear spreadsheets to support analysis of business decisions
  • Apply Pivot Tables to manage data in MS Excel
  • Formulate mathematical programming problems
  • Solve math programs using common technological tools
  • Build forecasting models using multiple regression and time series techniques
  • Perform and interpret the results of basic data mining applications
  • Formulate and solve multi-stage decision tree problems
  • Structure and formulate risk analysis problems
  • Provide solutions and alternatives to risk modeling problems using risk analysis technology
  • Utilize a variety of Add-Ins in MS Excel including Solver, Evolutionary Solver, Precision Tree and @ Risk
  • Communicate the results of analysis in managerial terms


Topics we covered


Business Analytics and
Modeling with Spreadsheets
Data Presentation, Description and Pivot Tables in MS Excel
Basic Optimization Modeling
Applications of Linear Programming
Networks and Integer Programming
Topics in Optimization
Regression Review
Data Mining
Time Series Forecasting
Topics in Forecasting
Simulation Modeling
Decision Analysis


Project 1:  Business Analytics                                             BUS 609    Murphy   Spring 2015

Analytics in the Real World

This individual project is worth 10% of Course Grade.  This should be done on your own.


Due:  Sunday, May 17 at 11:59pm by upload, and ALSO in hard copy by final exam period, Tuesday, May 19.


Deliverable: Approximately 3-5 page report, 1.5 spaced describing an analytics, management science or model challenge in the real world and the methods and/or technologies used to solve it.  Five (5) references are required which can be a combination of articles or links that support the writing in the report.  Exhibits and tables can be included in the text body of the report, and long tables and exhibits can be included as appendices.  All writing should be in the third person.


Students may pick any problem or set of problems, in any real-world context, from business (financial, marketing, operations, management, human resources, etc.), science, government or society.  The problem should be described in words including the challenge at hand and the implications of effective solutions to managers, customers, clients, tax-payers and/or human society.  The problem should be one that is currently being addressed or should be addressed.  Students could choose a problem from their place of work or desired industry/job.


The problem(s) should be described in detail.  This requires presenting it in a manner that would be required for understanding how to address it using the models and tools like those covered in BUS 609.  This could (should) include the data that is available, the mathematical technique(s) that is(are) applied and the tools (software/hardware) that are used to solve the problem.  Indication should be made as to why the technique is appropriate for this particular setting.


The current state of solutions to the problem should be described.  Where are modelers and decision makers in the process of finding good/effective solutions?  What is limiting the quality of the results if the results are not yet effective?  What makes the solutions found useful if they currently are?  What are the implications of an effective solution to the problem?


The last section of the report should discuss the future opportunities and challenges of solving the problem.  What will help solutions improve?  What limitations remain?