Predictive analysis entails using a level of one (or more) variables to predict the level of another (dependent) variable.  Regression analysis, in particular, is a useful predictive analysis technique in identifying/exploring relationships between one variable and another (bi-variate) or between one variable and several others (multi-variate).

For example, in studying customer satisfaction, regression analysis can uncover the drivers of satisfaction and a mathematical model can be developed, which may look something like the following:

Overall Satisfaction = b + b₁ (prompt service) + b₂ (wide selection) + b₃ (good value) + b₄ (value pricing) + e

Predictive Modeling in Sales & Marketing
Again, the general purpose of multiple regression is to learn more about the relationship between several independent or predictor variables and a dependent or criterion variable.  For example, a sales representative might track the performance of each product based on the volume of the average order, the types of optional features typically sold with the base product, the average sales to each client according to historical data, and/or a subjective rating of appeal of the brand for each account.

Once this information has been compiled for various products, it would be interesting to see whether and how these measures relate to the price for which a product is sold. For example, one might learn that the types of optional features selected is a better predictor of the price for which a product sells in a particular region than how much brand appeal that product has (subjective rating).

Predictive Modeling in Human Resources
Personnel professionals can use multiple regression procedures to determine equitable compensation. One can determine a number of factors or dimensions such as "amount of responsibility" or "number of people to supervise" that one believes to contribute to the value of a job.

The personnel analyst then usually conducts a salary survey among comparable companies in the market, recording the salaries and respective characteristics (i.e., values on dimensions) for different positions. This information can be used in a multiple regression analysis to build a regression equation.

Once this so-called regression line has been determined, the analyst can now easily construct a graph of the expected (predicted) salaries and the actual salaries of job incumbents in his or her company. Thus, the analyst is able to determine which position is underpaid (below the regression line) or overpaid (above the regression line), or paid equitably.

In general, predictive analysis allows the researcher to ask (and hopefully answer) the general question "what is the best predictor of ...".