Predicting tax avoidance by means of social network analytics
Predicting tax avoidance by means of social network analytics
This study predicts tax avoidance by means of social network analytics. We extend previous literature by being the first to build a predictive model including a larger variation of network features. We construct a network of firms connected through shared board membership. Then, we apply three analytical techniques, logistic regression, decision trees, and random forests; to create five models using either firm characteristics, network characteristics or different combinations of both. A random forest including firm characteristics, network characteristics of firms and network characteristics of board members provides the best performance with a minimal increase of 7 pp in AUC. Hence, including network effects significantly improves the predictive ability of tax avoidance models, implying that board members exhibit specific knowledge which can carry over across firms. We find that having board members with no connections to low-tax companies lowers the likelihood of being a low-tax firm. Similarly, the higher the average tax rate of the companies a board member is connected to, the lower the chance of being low-tax. On the other hand, being connected to more low-tax firms increases the probability of being low-tax. Consistent with prior literature on firm-specific variables, PP&E has a positive influence on the probability of being low-tax, while EBITDA has a negative effect. Our results are informative for companies as to the director expertise they want to attract in their boards. Additionally, financial analysts and regulatory agencies can use our insights to predict which firms are likely to be low-tax and potentially at risk.
Board interlocks, Predictive analytics, Social network analytics, Social ties, Tax avoidance, Tax planning
13-24
Lismont, Jasmien
ae828817-8188-4686-89b3-2438fa3ee3aa
Cardinaels, Eddy
c5b9b5b7-2dbf-47be-826e-d5a36eafb241
Bruynseels, Liesbeth
9c0a3100-b543-43ab-ba0f-114d21193bdd
De Groote, Sander
b2326d15-3069-49ea-85b0-405219a900bc
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Lemahieu, Wilfried
be4bae3f-12b9-417a-91a1-c3c264ffe068
Vanthienen, Jan
6f3d818f-0fce-46fa-966b-160e645caf6d
April 2018
Lismont, Jasmien
ae828817-8188-4686-89b3-2438fa3ee3aa
Cardinaels, Eddy
c5b9b5b7-2dbf-47be-826e-d5a36eafb241
Bruynseels, Liesbeth
9c0a3100-b543-43ab-ba0f-114d21193bdd
De Groote, Sander
b2326d15-3069-49ea-85b0-405219a900bc
Baesens, Bart
f7c6496b-aa7f-4026-8616-ca61d9e216f0
Lemahieu, Wilfried
be4bae3f-12b9-417a-91a1-c3c264ffe068
Vanthienen, Jan
6f3d818f-0fce-46fa-966b-160e645caf6d
Lismont, Jasmien, Cardinaels, Eddy, Bruynseels, Liesbeth, De Groote, Sander, Baesens, Bart, Lemahieu, Wilfried and Vanthienen, Jan
(2018)
Predicting tax avoidance by means of social network analytics.
Decision Support Systems, 108, .
(doi:10.1016/j.dss.2018.02.001).
Abstract
This study predicts tax avoidance by means of social network analytics. We extend previous literature by being the first to build a predictive model including a larger variation of network features. We construct a network of firms connected through shared board membership. Then, we apply three analytical techniques, logistic regression, decision trees, and random forests; to create five models using either firm characteristics, network characteristics or different combinations of both. A random forest including firm characteristics, network characteristics of firms and network characteristics of board members provides the best performance with a minimal increase of 7 pp in AUC. Hence, including network effects significantly improves the predictive ability of tax avoidance models, implying that board members exhibit specific knowledge which can carry over across firms. We find that having board members with no connections to low-tax companies lowers the likelihood of being a low-tax firm. Similarly, the higher the average tax rate of the companies a board member is connected to, the lower the chance of being low-tax. On the other hand, being connected to more low-tax firms increases the probability of being low-tax. Consistent with prior literature on firm-specific variables, PP&E has a positive influence on the probability of being low-tax, while EBITDA has a negative effect. Our results are informative for companies as to the director expertise they want to attract in their boards. Additionally, financial analysts and regulatory agencies can use our insights to predict which firms are likely to be low-tax and potentially at risk.
Text
Predicting tax avoidance by means of social network analytics
- Accepted Manuscript
More information
Accepted/In Press date: 1 February 2018
e-pub ahead of print date: 9 February 2018
Published date: April 2018
Keywords:
Board interlocks, Predictive analytics, Social network analytics, Social ties, Tax avoidance, Tax planning
Identifiers
Local EPrints ID: 420707
URI: http://eprints.soton.ac.uk/id/eprint/420707
ISSN: 0167-9236
PURE UUID: 96f92638-4dbc-4b2d-b23b-38f1787d4fdb
Catalogue record
Date deposited: 11 May 2018 16:30
Last modified: 18 Mar 2024 05:16
Export record
Altmetrics
Contributors
Author:
Jasmien Lismont
Author:
Eddy Cardinaels
Author:
Liesbeth Bruynseels
Author:
Sander De Groote
Author:
Wilfried Lemahieu
Author:
Jan Vanthienen
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
