Predictive Modeling | Multivariate Solutions

Predictive models are the mainstay of data driven decision making. The focus lies on establishing a mathematical equation as a model to represent the interactions between the different variables in consideration, and use them to predict or score customer behavior.

Multivariate Solutions employs a wide variety of models that can be applied to perform predictive analytics. Some of them are listed below:

Linear Regression Model
Discriminant Analysis
Discrete Choice Models
Logistic Regression
Multinomial Logistic Regression
Probit Regression
Time Series Models
CHAID Classification Trees
Structural Equations Models

Regression Analysis Positioning uses the most common predictive analytic method to distinguish between two types of customer and maximizes how to communicate to each.

Finding Supporters – Political Predictive Analytics uses a regression technique to target potential supporters for candidate Liz Anderson’s bid for Congress.

Measuring and Using Employee Satisfaction, a piece that illustrates ‘Within human resources the dependent variable should not only be defined by the HR goals of the employer … It should also include an evaluation of the impact on customer satisfaction,’ outlines a data-driven method to predict which attitudes will lower employee turnover.

Donor Predictive CHAID Tree uses a classification tree method to box in most-likely donors to a political party.

Campaigns and Elections – What is Driving the Vote? describes the successful employment of regression analysis to determine voter motives.

Predictive Regression Analysis explains how to employ the widely used and robust predictive technique made famous in Ian Ayres’ seminal work, SuperCrunchers.