Assignment 15 Regression Concepts

docx

School

Arizona State University *

*We aren’t endorsed by this school

Course

511

Subject

Business

Date

Apr 3, 2024

Type

docx

Pages

Uploaded by AgentQuetzal3025

Assignment 15: Regression Concepts Prasad Srinivas IFT 511: Analyzing Big Data Professor: Asmaa Elbadrawy Tuesday and Thursday (12:00 PM – 1:15 PM) November 4, 2023

1. Define the regression problem. Regression is an approach that helps establish a relationship, between one or more variables, also known as explanatory variables and a dependent variable. This method involves analyzing characteristics to understand and predict continuous target features. Regression is classified as learning because it involves transforming input observations into the target variable using a predefined function. 2. List five example problems that can be solved using regression. I. Making predictions, about the cost of a home by considering factors such as its size, location, and number of bedrooms. II. Estimating the amount of energy consumed by a household based on variables like temperature, time of day, and usage of appliances. III. Forecasting the demand for a product or service by analyzing sales data and market trends. IV. Assessing the impact of expenditure and teacher qualifications on students' test scores. V. Predicting the duration required to complete a software project based on factors such, as the number of lines of code and team size. 3. State the difference between linear and non-linear regression. Aspect Linear Regression Non-linear Regression Target Variable Type Interval Variable Discrete (Binary or Ordinal) Plot Appearance Results in a Straight-Line Plot Does Not Result in a Straight-Line Plot Suitable Models Linear Functions Quadratic, Cubic, Exponential, Logistic, etc. Common Applications Forecasting Company Sales Predicting Test Success Based on Study Hours Polynomial Powers for X Up to Power 1 or less Greater Than 1 at Least Once Primary Function y = a + bx Not Applicable (Doesn't Follow Linear Rules) 4. How do you determine whether linear or non-linear regression is more appropriate for a given problem? I. To determine if linear regression is appropriate, for a given problem we need to evaluate its ability to capture the curve pattern in our data effectively. If linear regression fails to do so, we should consider using regression instead. Nonlinear regression offers flexibility in accommodating a range of curve shapes. II. One way to determine this is by assessing whether the linear regression model accurately represents the data points. Based on how it fits we can decide between using linear or nonlinear regression. If the linear model does not accurately capture the curved pattern, in the data then nonlinear regression is an option.

5. List three example problems that can be solved using logistic regression. I. Determining whether an email is spam or not by analyzing its content and characteristics. II. Predicting the likelihood of a loan applicant defaulting on their loan considering their credit score and income. III. Evaluating the chances of a customer canceling their subscription service based on their usage patterns and demographic information.

Your preview ends here

Eager to read complete document? Join bartleby learn and gain access to the full version

Access to all documents
Unlimited textbook solutions
24/7 expert homework help

Related Documents

Chapter 15 Quiz.pdf

LEVIS JEANS.docx

behavioural economics.docx

Soto_SB4.docx

Appendix A Handout #3 With Solutions.docx

3GR0 Business Workbook-2024-Part4.docx

Assignment 14 Reading about Other Evaluation Metrics for Classifiers .docx

Assignment 7 Classification Examples .docx

week8.pdf

SAMcase (1).docx

FINAL ROLE PLAY prep.pdf

Spring 2024 MNGT 481 Live Case.docx

Recommended textbooks for you

Practical Management Science

Operations Management

ISBN:9781337406659

Author:WINSTON, Wayne L.

Publisher:Cengage,

Contemporary Marketing

Marketing

ISBN:9780357033777

Author:Louis E. Boone, David L. Kurtz

Publisher:Cengage Learning

Marketing

ISBN:9780357033791

Author:Pride, William M

Publisher:South Western Educational Publishing

SEE MORE TEXTBOOKS

Recommended textbooks for you

Practical Management Science
Operations Management
ISBN:9781337406659
Author:WINSTON, Wayne L.
Publisher:Cengage,
Contemporary Marketing
Marketing
ISBN:9780357033777
Author:Louis E. Boone, David L. Kurtz
Publisher:Cengage Learning
Marketing
Marketing
ISBN:9780357033791
Author:Pride, William M
Publisher:South Western Educational Publishing

Practical Management Science

Operations Management

ISBN:9781337406659

Author:WINSTON, Wayne L.

Publisher:Cengage,

Contemporary Marketing

Marketing

ISBN:9780357033777

Author:Louis E. Boone, David L. Kurtz

Publisher:Cengage Learning

Marketing

ISBN:9780357033791

Author:Pride, William M

Publisher:South Western Educational Publishing

SEE MORE TEXTBOOKS