Logistic regression is a commonly used tool to analyze binary classification problems. However, logisitic regression still faces the limitations of detecting nonlinearities and interactions in data. In this webinar, you will learn more advanced and intuitive machine learning techniques that improve on standard logistic regression in accuracy and other aspects. As an APPLIED example, we will demonstrate using a banking dataset where we will predict future financial stress of a loan applicant in order to determine whether they should be granted a loan. Although the focus is related to finance and loans, the concepts are relevant for anyone who actively uses logistic regression and wishes to improve accuracy and predictor understanding.
After you have mastered the data mining basics, explore new ways to squeeze out extra insight from your models and leverage the underlying methodology of Salford Systems' data mining software.
This series focuses on what Salford Systems calls “batteries,” which are pre-packaged scenarios that are inspired by how leading analysts structure their modeling work.
Learn: What is a surrogate? What makes a good surrogate? Why are surrogates important?
Segmentation (targeting, profiling, classification) is the process of dividing a database into distinct groups of individuals who share common characteristics. This is readily accomplished using modern data mining and machine learning techniques. The methods are easily implemented and work well with large datasets containing nonlinearities, interactions in the data, and a mix of categorical and numerical variables.
Understand the value of PRIORS EQUAL and PRIORS DATA in common classification problems in CART.
Learn to control the size of the maximal CART tree in two ways: Telling CART to stop early and limiting CART's freedom to produce small nodes.