OPRE 3333 Lecture Notes - Lecture 3: Solution Process, Linear Regression, Data Mining
25 Jun 2018
School
Department
Course
Professor
CH 1 + CH 3 INTRO & DATA VISUALIZATION
Business Analytics: an objective scientific process of transforming data into insightful decision making.
Uses data-driven/ fact-driven decision making.
Managers plan, coordinate and organize.
◦ Strategic decisions : higher-level issues abt overall direction of company , 3-5 yrs.
Tactical decisions:◦ how the organization should achieve the goals and objectives set by its strategy,
midlevel, 1 yr.
Operational decisions: operation managers run day to day operations.◦
Problem Solving and Decision Making
1. Recognizing the problem: a gap between what is happening and what we think should be
happening.
2. Defining the problem: complex to define a problem if many courses of action, several competing
objectives, external groups, time constraints etc.
3. Structuring the problem: stating goals, objectives, possible decisions, identifying restrictions and
defining clear metrics and acquiring data.
4. Analyzing the problem : experimentation (trial and error), statistical analysis, or a solution process.
5. Interpreting results and making a decision: Understand limitations and model assumptions
6. Implementing the solution : is the solution logical, does it work in real world, and provide adequate
training and resources to make this possible.
Models:
Mathematical modeling- Accurately represent reality, gives insight on info, saves $ and time and useful
to communicate problems.
Decision model- used to understand, analyze, or facilitate decision making.
- types of input
1) data (accurate or trash in-trash out)
2) external variables (inflation, demand)
3) decision variables (controllable)
- output
1) Performance measures.
2) behavioral measures.
Analytics
Descriptive Analytics- describes what has happened in the past. Exs: data queries, reports, descriptive
statistics, data visualization, data-mining techniques
Predictive Analytics- uses past data to predict the future or evaluate the impact of one variable or
another.
Exs: Linear regression, time series analysis, some data-mining techniques, and simulation are part of
this category. There is uncertainty and risk.
Prescriptive Analytics- Indicate the best course of action to take, the best possible
decision. Exs: optimization and decision analysis.
Objective function - the equation that minimizes (or maximizes) the quantity of interest.
find more resources at oneclass.com
find more resources at oneclass.com
Examples:
Revenue management in Airline Industry◦
Portfolio models in finance◦
Supply network design models in operations◦
Price markdown models in retailing◦
Challenges in quantitative analysis:
-conflicting viewpoints, outdated solutions
-trade off btwn complexity and ease of understanding.
-have to check validity of data
-only one answer maybe too limiting
Forecasting Subjective methods:
Historical analogy –analysis of past experiences◦
Delphi Method –panel of experts◦
Intuition◦
Qualitative methods:
use of expert judgment to develop forecasts
Quantitative forecasting methods can be used when:
(1) past information about the variable being forecast is available,
(2) the information can be quantified, and
(3) it is reasonable to assume that past is prologue
Eight Steps to Forecasting
1.Determine the use of the forecast—what objective are we trying to obtain?
2.Select the items or quantities that are to be forecasted.
3.Determine the time horizon of the forecast.
4.Select the forecasting model or models.
5.Gather the data needed to make the forecast.
6.Validate the forecasting model.
7.Make the forecast.
8.Implement the results.
Time series: sequence of evenly spaced observations of a variable measured at successive periods of
time. based solely on the past values of the variable, and other variables are ignored.
Time series patterns:
Horizontal: data fluctuates randomly around a constant mean over time (stationary time
series).
find more resources at oneclass.com
find more resources at oneclass.com
Document Summary
Ch 1 + ch 3 intro & data visualization. Business analytics: an objective scientific process of transforming data into insightful decision making. Managers plan, coordinate and organize: strategic decisions : higher-level issues abt overall direction of company , 3-5 yrs. how the organization should achieve the goals and objectives set by its strategy, Operational decisions: operation managers run day to day operations. midlevel, 1 yr. Mathematical modeling- accurately represent reality, gives insight on info, saves $ and time and useful to communicate problems. Decision model- used to understand, analyze, or facilitate decision making. Descriptive analytics- describes what has happened in the past. Exs: data queries, reports, descriptive statistics, data visualization, data-mining techniques. Predictive analytics- uses past data to predict the future or evaluate the impact of one variable or another. Exs: linear regression, time series analysis, some data-mining techniques, and simulation are part of this category. Prescriptive analytics- indicate the best course of action to take, the best possible decision.
