An effective call prediction model based on noisy mobile phone data

Iqbal H. Sarker; Ashad Kabir; Alan Colman; Jun Han

doi:10.1145/3123024.3123088

An effective call prediction model based on noisy mobile phone data

Iqbal H. Sarker, Ashad Kabir, Alan Colman, Jun Han

Swinburne University of Technology

Research output: Book chapter/Published conference paper › Conference paper › peer-review

4 Citations (Scopus)

Abstract

Noisy instance in mobile phone data is an important issue for modeling user phone call behavior, with many potential negative consequences. The accuracy of prediction may decrease, thereby increasing the complexity of inferred models and the number of training samples needed. In this paper, we present an effective phone call prediction model based on noisy mobile phone data in order to improve the prediction accuracy for individual mobile phone users. Experimental results on the real phone call log datasets show the effectiveness of our prediction model for individual mobile phone users.

Original language	English
Title of host publication	UbiComp/ISWC '17 adjunct
Subtitle of host publication	Proceedings of the 2017 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2017 ACM international symposium on wearable computers
Place of Publication	United States
Publisher	Association for Computing Machinery, Inc (ACM)
Pages	193-196
Number of pages	4
ISBN (Print)	9781450351904
DOIs	https://doi.org/10.1145/3123024.3123088
Publication status	Published - 2017
Event	ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp'17) - Grand Wailea, Wailea, Maui, United States Duration: 11 Sept 2017 → 15 Sept 2017 https://iswc.net/iswc17/ (Conference website (ISWC)) http://www.ubicomp.org/ubicomp2017/index.html (Conference website (Ubicomp)) https://dl.acm.org/citation.cfm?id=3123024&picked=prox (Conference proceedings)

Conference

Conference	ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp'17)
Country/Territory	United States
City	Wailea, Maui
Period	11/09/17 → 15/09/17
Other	The 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UBICOMP 2017) is the premier outlet for novel research contributions in ubiquitous and pervasive computing systems. It is the result of a merger of the two most renowned conferences in the field: Pervasive and UBICOMP. The 2017 International Symposium on Wearable Computers (ISWC 2017) is the premier forum for wearable computing and issues related to on-body and worn mobile technologies. It brings together researchers, product vendors, fashion designers, textile manufacturers, users, and related professionals. UBICOMP 2017 and ISWC 2017 will be held as a single event, featuring a single registration rate. Attendees of either conference will have full access to all tracks of the other. Register here to attend either conference.
Internet address	https://iswc.net/iswc17/ (Conference website (ISWC)) http://www.ubicomp.org/ubicomp2017/index.html (Conference website (Ubicomp)) https://dl.acm.org/citation.cfm?id=3123024&picked=prox (Conference proceedings)

Access to Document

10.1145/3123024.3123088

Cite this

Sarker, I. H., Kabir, A., Colman, A., & Han, J. (2017). An effective call prediction model based on noisy mobile phone data. In UbiComp/ISWC '17 adjunct: Proceedings of the 2017 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2017 ACM international symposium on wearable computers (pp. 193-196). Association for Computing Machinery, Inc (ACM). https://doi.org/10.1145/3123024.3123088

Sarker, Iqbal H. ; Kabir, Ashad ; Colman, Alan et al. / An effective call prediction model based on noisy mobile phone data. UbiComp/ISWC '17 adjunct: Proceedings of the 2017 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2017 ACM international symposium on wearable computers. United States : Association for Computing Machinery, Inc (ACM), 2017. pp. 193-196

@inproceedings{e13e57635a87490887f7a5cbe409c854,

title = "An effective call prediction model based on noisy mobile phone data",

abstract = "Noisy instance in mobile phone data is an important issue for modeling user phone call behavior, with many potential negative consequences. The accuracy of prediction may decrease, thereby increasing the complexity of inferred models and the number of training samples needed. In this paper, we present an effective phone call prediction model based on noisy mobile phone data in order to improve the prediction accuracy for individual mobile phone users. Experimental results on the real phone call log datasets show the effectiveness of our prediction model for individual mobile phone users.",

keywords = "Mobile Data Mining, Noisy Data, Naive Bayes Classiﬁer, Decision Tree, Phone Call Behavior",

author = "Sarker, {Iqbal H.} and Ashad Kabir and Alan Colman and Jun Han",

note = "Includes bibliographical references.; ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp'17) ; Conference date: 11-09-2017 Through 15-09-2017",

year = "2017",

doi = "10.1145/3123024.3123088",

language = "English",

isbn = "9781450351904",

pages = "193--196",

booktitle = "UbiComp/ISWC '17 adjunct",

publisher = "Association for Computing Machinery, Inc (ACM)",

url = "https://iswc.net/iswc17/, http://www.ubicomp.org/ubicomp2017/index.html, https://dl.acm.org/citation.cfm?id=3123024&picked=prox",

}

Sarker, IH, Kabir, A, Colman, A & Han, J 2017, An effective call prediction model based on noisy mobile phone data. in UbiComp/ISWC '17 adjunct: Proceedings of the 2017 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2017 ACM international symposium on wearable computers. Association for Computing Machinery, Inc (ACM), United States, pp. 193-196, ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp'17) , Wailea, Maui, Hawaii, United States, 11/09/17. https://doi.org/10.1145/3123024.3123088

An effective call prediction model based on noisy mobile phone data. / Sarker, Iqbal H.; Kabir, Ashad; Colman, Alan et al.
UbiComp/ISWC '17 adjunct: Proceedings of the 2017 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2017 ACM international symposium on wearable computers. United States: Association for Computing Machinery, Inc (ACM), 2017. p. 193-196.

Research output: Book chapter/Published conference paper › Conference paper › peer-review

TY - GEN

T1 - An effective call prediction model based on noisy mobile phone data

AU - Sarker, Iqbal H.

AU - Kabir, Ashad

AU - Colman, Alan

AU - Han, Jun

N1 - Includes bibliographical references.

PY - 2017

Y1 - 2017

N2 - Noisy instance in mobile phone data is an important issue for modeling user phone call behavior, with many potential negative consequences. The accuracy of prediction may decrease, thereby increasing the complexity of inferred models and the number of training samples needed. In this paper, we present an effective phone call prediction model based on noisy mobile phone data in order to improve the prediction accuracy for individual mobile phone users. Experimental results on the real phone call log datasets show the effectiveness of our prediction model for individual mobile phone users.

AB - Noisy instance in mobile phone data is an important issue for modeling user phone call behavior, with many potential negative consequences. The accuracy of prediction may decrease, thereby increasing the complexity of inferred models and the number of training samples needed. In this paper, we present an effective phone call prediction model based on noisy mobile phone data in order to improve the prediction accuracy for individual mobile phone users. Experimental results on the real phone call log datasets show the effectiveness of our prediction model for individual mobile phone users.

KW - Mobile Data Mining

KW - Noisy Data

KW - Naive Bayes Classiﬁer

KW - Decision Tree

KW - Phone Call Behavior

U2 - 10.1145/3123024.3123088

DO - 10.1145/3123024.3123088

M3 - Conference paper

SN - 9781450351904

SP - 193

EP - 196

BT - UbiComp/ISWC '17 adjunct

PB - Association for Computing Machinery, Inc (ACM)

CY - United States

T2 - ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp'17)

Y2 - 11 September 2017 through 15 September 2017

ER -

Sarker IH, Kabir A, Colman A, Han J. An effective call prediction model based on noisy mobile phone data. In UbiComp/ISWC '17 adjunct: Proceedings of the 2017 ACM international joint conference on pervasive and ubiquitous computing and proceedings of the 2017 ACM international symposium on wearable computers. United States: Association for Computing Machinery, Inc (ACM). 2017. p. 193-196 doi: 10.1145/3123024.3123088

An effective call prediction model based on noisy mobile phone data

Abstract

Conference

Access to Document

Fingerprint

Cite this