WPC_300 Mid_Term_Prep.docx.pdf

Mid-Term Prep

1st step: ask the right questions

1) Perform business discovery

2) Perform data discovery

3) Prepare data

4) Model data

5) Score and display

6) Evaluate and improve

Data: Collection, Cleaning, Analyses, Communication

Principles of Problem Framing

Tell an interesting and complete story

Find an appropriate solution framework

Routinize the procedure

Primary Data: Survey, Interviews, used a lot in marketing

Secondary Data: Proprietary database, internet data, stock/capital market data, accounting disclosure

data

Simulated Data: Data based on assumption and simulation

ETL = Extract, Transform, and Load

Different Types of Analytics **review slides** week1slideb

Descriptive – Historical. What are our sales last year?

Explanatory Analytics- why did our sales surge in November?

Predictive – what will be our likely revenue?

Prescriptive- what should we do if… or How do we….

Decision Making Biasis

**Analytics vs Heuristics

3 Principles of describing data- centrality, spread, and shape

Population mean – mu

Sample mean – x bar

Data spread = measures of variability

Range, interquartile range, mean absolute deviation, variance, standard deviation

Kurtosis – measures of skewness

Correlation coefficient is between -1 and 1. Farther from zero means stronger correlation. Close to zero

means no correlation. Correlation = covariance / standard deviation