The process of predictive modeling involves using a modeling database to discover relationships between a dependent variable and other explanatory variables, and then applying this model to other data sets containing the same explanatory variables. There are many methodologies available for building the model. One distinguishing characteristic between methodologies is the extent to which the influence of the explanatory variables on the prediction can be understood. The term "black box" is often used to describe a model for which the relationship between the data and the prediction is completely unknown.
Neural networking is often cited as a methodology that builds a black box. While tree models are characterized by "simple" if-then rules that can sometimes be easy to understand, a complex tree with many branches and leaves can be very difficult to understand. With regression models, on the other hand, there is usually a straightforward relationship between the explanatory variables and the prediction.
Register or login for access to this item and much more
All Information Management content is archived after seven days.
Community members receive:
- All recent and archived articles
- Conference offers and updates
- A full menu of enewsletter options
- Web seminars, white papers, ebooks
Already have an account? Log In
Don't have an account? Register for Free Unlimited Access