DAY 1 MORNING
 

1) Basics of Modeling 

    a) What is modeling?
    b) Stages in the modeling process (CRISP-DM)
        i) Business Understanding
        ii) Data Understanding
            (1) Collect data
            (2) Describe and explore data
            (3) Assess data quality
        iii) Data Preparation
            (1) Clean data
                (a) Missing values
                (b) Miscoded data
            (2) Construct data
            (3) Sample data
        iv) Modeling
            (1) Select modeling techniques
            (2) Build model
            (3) Assess model
         v) Evaluation
            (1) Evaluate Results
                (a) Model accuracy
                (b) Model interpretation
            (2) Review Modeling Process
            (3) Accept or Reject Model
        vi) Deployment
            (1) Determine deployment method
            (2) Devise model maintenance plan

2) A simple modeling example
    a) Layout of Affinium Model
    b) The Data Import Wizard/ Importing the vetresp.dat file
    c) The Modeling Wizard/ building the Quick Model
        i) Specifying the response variable
        ii) Selecting input variables
        iii) Importing the data dictionary
        iv) Selecting the modeling level
 

DAY 1- AFTERNOON

    d) Viewing sample reports
        i) The Data Dictionary report
        ii) The Variable Summary report
        iii) The Variable Numeric report
        iv) The Variable Profile report
        v) The Modeling Summary report
        vi) The Model Sensitivity Summary report
        vii) The Model Variable Sensitivity report
        viii) The Model Performance report
        ix) The Campaign report
        x) The Model Details report
        xi) The Log report

3) A more detailed view
    a) Data types
        i) Money
        ii) Date
        iii) Time
        iv) Telephone/Access #
        v) Flag
        vi) Categorical
        vii) Quantity
        viii) Descriptive/Names
        ix) City
        x) Zip Code
        xi) Country
        xii) Continent
        xiii) Time Zone
        xiv) As Is
    b) Data preparation- data cleanup function
    c) Affinium Model and data preprocessing
        i) Money- log ratio preprocessing
        ii) Ordered numeric variables
            (1) Polynomial
            (2) Unsorted chi-squared binning
            (3) Z-score normalization
        iii) Categorical variables- chi-squared binning


DAY 2- MORNING

    d) Algorithm overview
        i) RFM
        ii) Bayes
        iii) Linear regression
        iv) Logistic regression
        v) Backpropogation neural network
        vi) ChAID
        vii) CART
        viii) Manual

4) Scoring Models
    a) Scoring options
    b) Deployment options
    c) Understanding reports and customizing

5) Other modules
    a) Customer Valuator
    b) Cross Seller
    c) Customer Segmenter


DAY 2- AFTERNOON

6) Client data and projects, questions and answers