negSPUC: Trees-Based Single-Phase High-Utility Itemset Mining Algorithm with Negative Profit Values

B. Anup Bhat; S. V. Harish; M. Geetha

doi:10.1007/978-981-19-5868-7_55

negSPUC: Trees-Based Single-Phase High-Utility Itemset Mining Algorithm with Negative Profit Values

B. Anup Bhat, S. V. Harish^*, M. Geetha

^*Corresponding author for this work

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

Abstract

High-utility itemset mining (HUIM) extracts novel, non-trivial itemsets by incorporating the revenue generated by the purchased items from voluminous customer transaction databases. Although, most of the tree-based algorithms in the literature are two-phased, recently a single-phase algorithm called single-phase utility computation (SPUC) has been proposed. However, such conventional algorithms mine only a subset of HUIs when certain items bear negative profit values in the database. In this study, negSPUC algorithm has been proposed where the two compact tree structures—Utility Count Tree and String Utility Tree—are restructured to handle items bearing negative profits. negSPUC with path-based and overestimated utility pruning strategies can mine a complete set of HUIs when transaction database contains both positive and/or negative profit values. Further, experimental evaluation on synthetic and real data sets demonstrates the efficiency of negSPUC over HUINIV-Mine algorithm.

Original language	English
Title of host publication	Machine Learning, Image Processing, Network Security and Data Sciences - Select Proceedings of 3rd International Conference on MIND 2021
Editors	Rajesh Doriya, Badal Soni, Anupam Shukla, Xiao-Zhi Gao
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	739-750
Number of pages	12
ISBN (Print)	9789811958670
DOIs	https://doi.org/10.1007/978-981-19-5868-7_55
Publication status	Published - 2023
Event	3rd International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2021 - Raipur, India Duration: 11-12-2021 → 12-12-2021

Publication series

Name	Lecture Notes in Electrical Engineering
Volume	946
ISSN (Print)	1876-1100
ISSN (Electronic)	1876-1119

Conference

Conference	3rd International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2021
Country/Territory	India
City	Raipur
Period	11-12-21 → 12-12-21

All Science Journal Classification (ASJC) codes

Industrial and Manufacturing Engineering

Access to Document

10.1007/978-981-19-5868-7_55

Cite this

Anup Bhat, B., Harish, S. V., & Geetha, M. (2023). negSPUC: Trees-Based Single-Phase High-Utility Itemset Mining Algorithm with Negative Profit Values. In R. Doriya, B. Soni, A. Shukla, & X.-Z. Gao (Eds.), Machine Learning, Image Processing, Network Security and Data Sciences - Select Proceedings of 3rd International Conference on MIND 2021 (pp. 739-750). (Lecture Notes in Electrical Engineering; Vol. 946). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-19-5868-7_55

Anup Bhat, B. ; Harish, S. V. ; Geetha, M. / negSPUC : Trees-Based Single-Phase High-Utility Itemset Mining Algorithm with Negative Profit Values. Machine Learning, Image Processing, Network Security and Data Sciences - Select Proceedings of 3rd International Conference on MIND 2021. editor / Rajesh Doriya ; Badal Soni ; Anupam Shukla ; Xiao-Zhi Gao. Springer Science and Business Media Deutschland GmbH, 2023. pp. 739-750 (Lecture Notes in Electrical Engineering).

@inproceedings{e143efcef3be41499eaebb4ec2ac190f,

title = "negSPUC: Trees-Based Single-Phase High-Utility Itemset Mining Algorithm with Negative Profit Values",

abstract = "High-utility itemset mining (HUIM) extracts novel, non-trivial itemsets by incorporating the revenue generated by the purchased items from voluminous customer transaction databases. Although, most of the tree-based algorithms in the literature are two-phased, recently a single-phase algorithm called single-phase utility computation (SPUC) has been proposed. However, such conventional algorithms mine only a subset of HUIs when certain items bear negative profit values in the database. In this study, negSPUC algorithm has been proposed where the two compact tree structures—Utility Count Tree and String Utility Tree—are restructured to handle items bearing negative profits. negSPUC with path-based and overestimated utility pruning strategies can mine a complete set of HUIs when transaction database contains both positive and/or negative profit values. Further, experimental evaluation on synthetic and real data sets demonstrates the efficiency of negSPUC over HUINIV-Mine algorithm.",

author = "{Anup Bhat}, B. and Harish, {S. V.} and M. Geetha",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.; 3rd International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2021 ; Conference date: 11-12-2021 Through 12-12-2021",

year = "2023",

doi = "10.1007/978-981-19-5868-7_55",

language = "English",

isbn = "9789811958670",

series = "Lecture Notes in Electrical Engineering",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "739--750",

editor = "Rajesh Doriya and Badal Soni and Anupam Shukla and Xiao-Zhi Gao",

booktitle = "Machine Learning, Image Processing, Network Security and Data Sciences - Select Proceedings of 3rd International Conference on MIND 2021",

address = "Germany",

}

Anup Bhat, B , Harish, SV & Geetha, M 2023, negSPUC: Trees-Based Single-Phase High-Utility Itemset Mining Algorithm with Negative Profit Values. in R Doriya, B Soni, A Shukla & X-Z Gao (eds), Machine Learning, Image Processing, Network Security and Data Sciences - Select Proceedings of 3rd International Conference on MIND 2021. Lecture Notes in Electrical Engineering, vol. 946, Springer Science and Business Media Deutschland GmbH, pp. 739-750, 3rd International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2021, Raipur, India, 11-12-21. https://doi.org/10.1007/978-981-19-5868-7_55

negSPUC: Trees-Based Single-Phase High-Utility Itemset Mining Algorithm with Negative Profit Values. / Anup Bhat, B.; Harish, S. V.; Geetha, M.
Machine Learning, Image Processing, Network Security and Data Sciences - Select Proceedings of 3rd International Conference on MIND 2021. ed. / Rajesh Doriya; Badal Soni; Anupam Shukla; Xiao-Zhi Gao. Springer Science and Business Media Deutschland GmbH, 2023. p. 739-750 (Lecture Notes in Electrical Engineering; Vol. 946).

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

TY - GEN

T1 - negSPUC

T2 - 3rd International Conference on Machine Learning, Image Processing, Network Security and Data Sciences, MIND 2021

AU - Anup Bhat, B.

AU - Harish, S. V.

AU - Geetha, M.

PY - 2023

Y1 - 2023

N2 - High-utility itemset mining (HUIM) extracts novel, non-trivial itemsets by incorporating the revenue generated by the purchased items from voluminous customer transaction databases. Although, most of the tree-based algorithms in the literature are two-phased, recently a single-phase algorithm called single-phase utility computation (SPUC) has been proposed. However, such conventional algorithms mine only a subset of HUIs when certain items bear negative profit values in the database. In this study, negSPUC algorithm has been proposed where the two compact tree structures—Utility Count Tree and String Utility Tree—are restructured to handle items bearing negative profits. negSPUC with path-based and overestimated utility pruning strategies can mine a complete set of HUIs when transaction database contains both positive and/or negative profit values. Further, experimental evaluation on synthetic and real data sets demonstrates the efficiency of negSPUC over HUINIV-Mine algorithm.

AB - High-utility itemset mining (HUIM) extracts novel, non-trivial itemsets by incorporating the revenue generated by the purchased items from voluminous customer transaction databases. Although, most of the tree-based algorithms in the literature are two-phased, recently a single-phase algorithm called single-phase utility computation (SPUC) has been proposed. However, such conventional algorithms mine only a subset of HUIs when certain items bear negative profit values in the database. In this study, negSPUC algorithm has been proposed where the two compact tree structures—Utility Count Tree and String Utility Tree—are restructured to handle items bearing negative profits. negSPUC with path-based and overestimated utility pruning strategies can mine a complete set of HUIs when transaction database contains both positive and/or negative profit values. Further, experimental evaluation on synthetic and real data sets demonstrates the efficiency of negSPUC over HUINIV-Mine algorithm.

UR - http://www.scopus.com/inward/record.url?scp=85148020010&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85148020010&partnerID=8YFLogxK

U2 - 10.1007/978-981-19-5868-7_55

DO - 10.1007/978-981-19-5868-7_55

M3 - Conference contribution

AN - SCOPUS:85148020010

SN - 9789811958670

T3 - Lecture Notes in Electrical Engineering

SP - 739

EP - 750

BT - Machine Learning, Image Processing, Network Security and Data Sciences - Select Proceedings of 3rd International Conference on MIND 2021

A2 - Doriya, Rajesh

A2 - Soni, Badal

A2 - Shukla, Anupam

A2 - Gao, Xiao-Zhi

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 11 December 2021 through 12 December 2021

ER -

Anup Bhat B , Harish SV , Geetha M. negSPUC: Trees-Based Single-Phase High-Utility Itemset Mining Algorithm with Negative Profit Values. In Doriya R, Soni B, Shukla A, Gao XZ, editors, Machine Learning, Image Processing, Network Security and Data Sciences - Select Proceedings of 3rd International Conference on MIND 2021. Springer Science and Business Media Deutschland GmbH. 2023. p. 739-750. (Lecture Notes in Electrical Engineering). doi: 10.1007/978-981-19-5868-7_55