Restricted multi-pruning of decision trees

Mohammad Azad; Igor Chikalov; Mikhail Moshkov; Shahid Hussain

doi:10.1142/9789813273238_0049

Restricted multi-pruning of decision trees

Mohammad Azad, Igor Chikalov, Mikhail Moshkov, Shahid Hussain

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The trade-off between the decision tree size and good classification accuracy is a research challenge. It can be achieved if we create multiple pruned trees from the set of Pareto optimal points using dynamic programming approach (multi-pruning process). However, this process can be extensively slow. We consider a modification of the multi-pruning process (restricted multi-pruning) that requires less memory and time but usually keeps the accuracy of the constructed classifiers.

Original language	English (US)
Title of host publication	Data Science and Knowledge Engineering for Sensing Decision Support
Publisher	World Scientific
ISBN (Print)	9789813273221
DOIs	https://doi.org/10.1142/9789813273238_0049
State	Published - Jul 30 2018

Access to Document

10.1142/9789813273238_0049

Cite this

@inproceedings{bfaf436aa5ba4fffa73e8dc3d69fa563,

title = "Restricted multi-pruning of decision trees",

abstract = "The trade-off between the decision tree size and good classification accuracy is a research challenge. It can be achieved if we create multiple pruned trees from the set of Pareto optimal points using dynamic programming approach (multi-pruning process). However, this process can be extensively slow. We consider a modification of the multi-pruning process (restricted multi-pruning) that requires less memory and time but usually keeps the accuracy of the constructed classifiers.",

author = "Mohammad Azad and Igor Chikalov and Mikhail Moshkov and Shahid Hussain",

note = "KAUST Repository Item: Exported on 2021-03-31",

year = "2018",

month = jul,

day = "30",

doi = "10.1142/9789813273238_0049",

language = "English (US)",

isbn = "9789813273221",

booktitle = "Data Science and Knowledge Engineering for Sensing Decision Support",

publisher = "World Scientific",

address = "United States",

}

TY - GEN

T1 - Restricted multi-pruning of decision trees

AU - Azad, Mohammad

AU - Chikalov, Igor

AU - Moshkov, Mikhail

AU - Hussain, Shahid

N1 - KAUST Repository Item: Exported on 2021-03-31

PY - 2018/7/30

Y1 - 2018/7/30

N2 - The trade-off between the decision tree size and good classification accuracy is a research challenge. It can be achieved if we create multiple pruned trees from the set of Pareto optimal points using dynamic programming approach (multi-pruning process). However, this process can be extensively slow. We consider a modification of the multi-pruning process (restricted multi-pruning) that requires less memory and time but usually keeps the accuracy of the constructed classifiers.

AB - The trade-off between the decision tree size and good classification accuracy is a research challenge. It can be achieved if we create multiple pruned trees from the set of Pareto optimal points using dynamic programming approach (multi-pruning process). However, this process can be extensively slow. We consider a modification of the multi-pruning process (restricted multi-pruning) that requires less memory and time but usually keeps the accuracy of the constructed classifiers.

UR - http://hdl.handle.net/10754/668410

UR - https://www.worldscientific.com/doi/abs/10.1142/9789813273238_0049

U2 - 10.1142/9789813273238_0049

DO - 10.1142/9789813273238_0049

M3 - Conference contribution

SN - 9789813273221

BT - Data Science and Knowledge Engineering for Sensing Decision Support

PB - World Scientific

ER -

Restricted multi-pruning of decision trees

Abstract

Access to Document

Other files and links

Fingerprint

Cite this