scispace - formally typeset
Search or ask a question
Topic

Decision tree model

About: Decision tree model is a research topic. Over the lifetime, 2256 publications have been published within this topic receiving 38142 citations.


Papers
More filters
01 Jan 2005
TL;DR: In this article, a decision tree model was created that predicts forest parcel size from spatially explicit predictor variables: population density, State, percentage forest land cover, and road density.
Abstract: A method for analyzing and mapping forest parcel sizes in the Northeastern United States is presented. A decision tree model was created that predicts forest parcel size from spatially explicit predictor variables: population density, State, percentage forest land cover, and road density. The model correctly predicted parcel size for 60 percent of the observations in a validation data set (weighted kappa = 0.45). This decision tree model was used to create a map representing the average forest parcel size across the region.

1 citations

Patent
17 Jan 2020
TL;DR: In this paper, the authors proposed a health management method based on a logistic regression model and a decision tree model, which comprises the following steps of collecting body index data, genetic disease history data and the corresponding target variable of each individual.
Abstract: The invention provides a health management method based on a logistic regression model and a decision tree model. The method comprises the following steps of: collecting body index data, genetic disease history data and the corresponding target variable of each individual, wherein the target variable is determination of whether the individual considers the health of the individual or not; modelingthe influence of genetic diseases on health by utilizing a decision tree model; wherein the input data of the decision tree model is genetic disease history data, and the target variable of the decision tree model is determination of whether the individual considers own health or not; by using a logistic regression model to perform modeling of health management; obtaining the physical index dataand genetic disease history data of a certain individual in real time; and inputting the genetic disease history data into the decision tree model to obtain the score of the genetic history of the current individual for health, and jointly inputting the score and the body index data of the current individual into the trained logistic regression model to obtain a model result composed of n fields with minimum p values output by the logistic regression model.

1 citations

Proceedings Article
01 Jan 2006
TL;DR: A new evaluation rule is presented to determine candidate splits in decision tree classifiers that reduces the size of the resulting tree, while maintaining the tree’s accuracy.
Abstract: Decision Trees are well known for their training efficiency and their interpretable knowledge representation. They apply a greedy search and a divide-and-conquer approach to learn patterns. The greedy search is based on the evaluation criterion on the candidate splits at each node. Although research has been performed on various such criteria, there is no significant improvement from the classical split approaches introduced in the early decision tree literature. This paper presents a new evaluation rule to determine candidate splits in decision tree classifiers. The experiments show that this new evaluation rule reduces the size of the resulting tree, while maintaining the tree’s accuracy.

1 citations

Proceedings ArticleDOI
01 Sep 2006
TL;DR: This paper derives an efficient method to determine the Maximum A-posteriori Probability model from a large set of context trees.
Abstract: Context tree models are Markov models where the conditioning is a string of previous symbols of variable length. These models are applicable for the modelling of natural languages and computer data. Also a decision tree can be seen as a context tree model. In this paper we derive an efficient method to determine the Maximum A-posteriori Probability model from a large set of context trees.

1 citations

Proceedings ArticleDOI
01 Feb 2020
TL;DR: The genetic algorithm dynamic optimization decision tree input attribute set financial crisis prediction method makes use of the advantages of decision tree knowledge, and overcomes the over fitting defects of traditional decision tree method when it trains the decision tree model with the pre-selected static attribute set.
Abstract: Based on the analysis of the spatial geometric significance of single classifier financial crisis prediction method, a new artificial intelligence single classifier financial crisis prediction approach is proposed, that is, the genetic algorithm dynamic optimization decision tree input attribute set financial crisis prediction method. The scheme makes use of the advantages of decision tree knowledge, and overcomes the over fitting defects of traditional decision tree method when it trains the decision tree model with the pre-selected static attribute set. It emphasizes the modeling idea of dynamic training decision tree with the goal of generalization prediction accuracy. The experimental results show that our method breaks through the limitation of using static input attribute set to model decision tree, improves the generalization performance of decision tree, reduces over fitting phenomenon, and improves the generalization prediction ability of decision tree financial crisis prediction model.

1 citations


Network Information
Related Topics (5)
Cluster analysis
146.5K papers, 2.9M citations
80% related
Artificial neural network
207K papers, 4.5M citations
78% related
Fuzzy logic
151.2K papers, 2.3M citations
77% related
The Internet
213.2K papers, 3.8M citations
77% related
Deep learning
79.8K papers, 2.1M citations
77% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
202310
202224
2021101
2020163
2019158
2018121