Outlier detection in financial statements

A text mining method

S. S. Kamaruddin, Abdul Razak Hamdan, Azuraliza Abu Bakar, F. Mat Nor

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper presents a text mining methodology to extract outlying knowledge from a collection of financial statements. The main idea is to extract relevant financial performance indicators and discover implicit textual description of the indicators. The extracted information was represented using a network language i.e. conceptual graph. Outlier mining was performed on the conceptual graph representation using a deviation based method. Experiments were carried out to evaluate the effectiveness of the proposed method. Results show that the proposed method is able to excerpt outlying knowledge from the financial statements with accuracy comparable to human experts.

Original languageEnglish
Title of host publicationWIT Transactions on Information and Communication Technologies
Pages71-82
Number of pages12
Volume42
DOIs
Publication statusPublished - 2009
Event10th International Conference on Data Mining, Detection, Protection and Security, Data Mining 2009 - Crete
Duration: 27 May 200929 May 2009

Other

Other10th International Conference on Data Mining, Detection, Protection and Security, Data Mining 2009
CityCrete
Period27/5/0929/5/09

Fingerprint

Experiments
Outlier detection
Text mining
Financial statements
Graph
Performance indicators
Outliers
Experiment
Deviation
Language
Methodology
Financial performance

Keywords

  • Conceptual graphs
  • Deviation based outlier mining method
  • Information extraction
  • Outlier mining in text
  • Text mining

ASJC Scopus subject areas

  • Management Information Systems
  • Computer Science(all)

Cite this

Kamaruddin, S. S., Hamdan, A. R., Abu Bakar, A., & Mat Nor, F. (2009). Outlier detection in financial statements: A text mining method. In WIT Transactions on Information and Communication Technologies (Vol. 42, pp. 71-82) https://doi.org/10.2495/DATA090081

Outlier detection in financial statements : A text mining method. / Kamaruddin, S. S.; Hamdan, Abdul Razak; Abu Bakar, Azuraliza; Mat Nor, F.

WIT Transactions on Information and Communication Technologies. Vol. 42 2009. p. 71-82.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kamaruddin, SS, Hamdan, AR, Abu Bakar, A & Mat Nor, F 2009, Outlier detection in financial statements: A text mining method. in WIT Transactions on Information and Communication Technologies. vol. 42, pp. 71-82, 10th International Conference on Data Mining, Detection, Protection and Security, Data Mining 2009, Crete, 27/5/09. https://doi.org/10.2495/DATA090081
Kamaruddin SS, Hamdan AR, Abu Bakar A, Mat Nor F. Outlier detection in financial statements: A text mining method. In WIT Transactions on Information and Communication Technologies. Vol. 42. 2009. p. 71-82 https://doi.org/10.2495/DATA090081
Kamaruddin, S. S. ; Hamdan, Abdul Razak ; Abu Bakar, Azuraliza ; Mat Nor, F. / Outlier detection in financial statements : A text mining method. WIT Transactions on Information and Communication Technologies. Vol. 42 2009. pp. 71-82
@inproceedings{9594de37b0c2433fb96bc0bad54859c5,
title = "Outlier detection in financial statements: A text mining method",
abstract = "This paper presents a text mining methodology to extract outlying knowledge from a collection of financial statements. The main idea is to extract relevant financial performance indicators and discover implicit textual description of the indicators. The extracted information was represented using a network language i.e. conceptual graph. Outlier mining was performed on the conceptual graph representation using a deviation based method. Experiments were carried out to evaluate the effectiveness of the proposed method. Results show that the proposed method is able to excerpt outlying knowledge from the financial statements with accuracy comparable to human experts.",
keywords = "Conceptual graphs, Deviation based outlier mining method, Information extraction, Outlier mining in text, Text mining",
author = "Kamaruddin, {S. S.} and Hamdan, {Abdul Razak} and {Abu Bakar}, Azuraliza and {Mat Nor}, F.",
year = "2009",
doi = "10.2495/DATA090081",
language = "English",
isbn = "9781845641849",
volume = "42",
pages = "71--82",
booktitle = "WIT Transactions on Information and Communication Technologies",

}

TY - GEN

T1 - Outlier detection in financial statements

T2 - A text mining method

AU - Kamaruddin, S. S.

AU - Hamdan, Abdul Razak

AU - Abu Bakar, Azuraliza

AU - Mat Nor, F.

PY - 2009

Y1 - 2009

N2 - This paper presents a text mining methodology to extract outlying knowledge from a collection of financial statements. The main idea is to extract relevant financial performance indicators and discover implicit textual description of the indicators. The extracted information was represented using a network language i.e. conceptual graph. Outlier mining was performed on the conceptual graph representation using a deviation based method. Experiments were carried out to evaluate the effectiveness of the proposed method. Results show that the proposed method is able to excerpt outlying knowledge from the financial statements with accuracy comparable to human experts.

AB - This paper presents a text mining methodology to extract outlying knowledge from a collection of financial statements. The main idea is to extract relevant financial performance indicators and discover implicit textual description of the indicators. The extracted information was represented using a network language i.e. conceptual graph. Outlier mining was performed on the conceptual graph representation using a deviation based method. Experiments were carried out to evaluate the effectiveness of the proposed method. Results show that the proposed method is able to excerpt outlying knowledge from the financial statements with accuracy comparable to human experts.

KW - Conceptual graphs

KW - Deviation based outlier mining method

KW - Information extraction

KW - Outlier mining in text

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=71649106534&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=71649106534&partnerID=8YFLogxK

U2 - 10.2495/DATA090081

DO - 10.2495/DATA090081

M3 - Conference contribution

SN - 9781845641849

VL - 42

SP - 71

EP - 82

BT - WIT Transactions on Information and Communication Technologies

ER -