Online Program Home
My Program

Abstract Details

Activity Number: 589 - Topics in Data Mining, Forecasting, and Bayesian Inference for National Security
Type: Contributed
Date/Time: Wednesday, August 1, 2018 : 2:00 PM to 3:50 PM
Sponsor: Section on Statistics in Defense and National Security
Abstract #329761
Title: Optimization of Decision Trees by Delaying the Split Decision
Author(s): Kyle Caudle* and Larry Pyeatt and Christer Karlsson and Randy Hoover
Companies: South Dakota School of Mines and Technology and South Dakota School of Mines and Technology and South Dakota School of Mines and Technology and South Dakota School of Mines and Technology
Keywords: Decision trees; Forecasting; Prediction
Abstract:

Classification and Regression trees (CART) are non-linear prediction models dating back to Breiman's work in the 1980's. These models are often thought of as decision trees whereby the feature space is divided into a tree-like structure based on specific levels of the independent variables. The basic CART methodology cycles through all variables and levels of the variables until it finds a partition of the feature space that minimizes the total impurity of the tree. CART is a greedy algorithm because it just looks for the split point that gives you the largest reduction in impurity. Our approach delays the split decision one or more levels.

In today's battle space, incoming threats are very often difficult to ascertain. Additionally, these threats are continually evolving at such a high rate of speed that allocation of assets by military leaders is exceedingly challenging. A decision tree can be used to automatically sift and interpret large volumes of information. Producing a decision tree with the best predictability would have far reaching applications within the military as well as sectors of government and industry.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program