Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
AI & SOCIETY
Published in: AI & SOCIETY 2/2024

23-06-2022 | Original Paper

What do we really know about the drivers of undeclared work? An evaluation of the current state of affairs using machine learning

Author: Josip Franic

Published in: AI & SOCIETY | Issue 2/2024

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

It is nowadays widely understood that undeclared work cannot be efficiently combated without a holistic view on the mechanisms underlying its existence. However, the question remains whether we possess all the pieces of the holistic puzzle. To fill the gap, in this paper, we test if the features so far known to affect the behaviour of taxpayers are sufficient to detect noncompliance with outstanding precision. This is done by training seven supervised machine learning models on the compilation of data from the 2019 Special Eurobarometer on undeclared work and relevant figures from other sources. The conducted analysis not only does attest to the completeness of our knowledge concerning the drivers of undeclared work but also paves the way for wide usage of artificial intelligence in monitoring and confronting this detrimental practice. The study, however, exposes the necessity of having at disposal considerably larger datasets compared to those currently available if successful real-world applications of machine learning are to be achieved in this field. Alongside the apparent theoretical contribution, this paper is thus also expected to be of particular importance for policymakers, whose efforts to tackle tax evasion will have to be expedited in the period after the COVID-19 pandemic.
previous article The autonomous choice architect
next article Are AI systems biased against the poor? A machine learning analysis using Word2Vec and GloVe embeddings

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now
Footnotes
1
Despite some earlier research on this topic (e.g., Geertz, 1963; Lewis, 1954), Hart's presentation to the Conference on urban unemployment in Africa is considered to be the turning point in this respect. His terminology was soon adopted and popularised by the International Labour Organization (ILO, 1972, 1993, 2002).
 
2
As a side effect, more than 40 different names have been used to denote unregulated work, each of them representing slightly different (but to a large extent overlapping) group of activities (Williams, 2004). Besides introducing additional confusion for practitioners dealing with this complex phenomenon, the terminological disunity also poses significant challenges for academics in their search of robust estimation methods.
 
3
The idea of undeclared work as a rational choice was first presented by Allingham and Sandmo (1972) in their theoretical paper on income tax evasion.
 
4
This applies primarily to deep learning, but other branches of this field also show remarkable achievements.
 
5
Approximately 1,000 persons aged 15 or more were interviewed in each member state following a multi-stage random (probability) sampling procedure. For more details on methodology, see European Commission (2020).
 
6
It is important to note that only the labour supply side of the phenomenon will be evaluated here. However, the approach applied in the rest of this paper can be easily adapted to the demand for unregistered employees/subcontractors, purchase of undeclared goods and services, and alike forms of violation.
 
7
Since the goal of a typical supervised learning model is to maximise accuracy, the computer can easily figure out that predicting majority-class outcome for each and every training set member is the most elegant solution (see for instance Johnson & Khoshgoftaar, 2019). In our case, this means that the model would be correct in 100*(1- (950/26,514)) = 96.42% of cases if always foreseeing nonparticipation in undeclared work, which might appear satisfactory from the perspective of this artificial intelligence and prevent it from further learning.
 
8
Synthetic minority oversampling (SMOTE) and dimensionality reduction using principal component analysis, which often yield models with better out-of-sample predictions, were also considered as possible solutions to this problem. However, the results were inferior to the ones based on reweighting.
 
9
In fact, unregularized versions of these two models were able to perfectly separate positive and negative training examples.
 
10
Specification details are given in Appendix 2.
 
Literature
Allingham MG, Sandmo A (1972) Income tax evasion: a theoretical analysis. J Public Econ 1(2):323–338CrossRef
Alm J, Torgler B (2006) Culture differences and tax morale in the United States and in Europe. J Econ Psychol 27(2006):224–246CrossRef
Alm J, Cherry T, Jones M, McKee M (2010) Taxpayer information assistance services and tax compliance behavior. J Econ Psychol 31(4):577–586CrossRef
Alm J, Clark J, Leibel K (2016) Enforcement, socioeconomic diversity, and tax filing compliance in the United States. South Econ J 82(3):725–747CrossRef
Alm J, Bloomquist KM, McKee M (2017) When you know your neighbour pays taxes: information, peer effects and tax compliance. Fisc Stud 38(4):587–613CrossRef
Ameyaw B, Dzaka D (2016) Determinants of tax evasion: empirical evidence from Ghana. Mod Econ 07(14):1653–1664CrossRef
Annis S, Franks J (1989) The idea, ideology, and economics of the informal sector; the case of Peru. Grassroots Dev 13(1):9–23
Arendt L, Grabowski W, Kukulak-Dolata I (2020) County-level patterns of undeclared work: An empirical analysis of a highly diversified region in the European Union. Soc Indic Res 149(1):271–295CrossRef
Athey S, Imbens GW (2019) Machine learning methods that economists should know about. Annu Rev Econ 11:685–725CrossRef
Barone G, Mocetti S (2011) Tax morale and public spending inefficiency. Int Tax Public Financ 18(6):724–749CrossRef
Benk S, Budak T, Yüzba B, Mohdali R (2016) The impact of religiosity on tax compliance among Turkish self-employed taxpayers. Religions 7(4):1–10CrossRef
Blackwell C (2010) Meta-analysis of incentive effects in tax compliance experiments. In: Alm J, Martinez-Vazquez J, Torgler B (eds) Developing alternative frameworks for explaining tax compliance. Routledge, London, pp 97–112
Bloomquist KM (2003) Tax evasion, income inequality and opportunity costs of tax compliance. In: Proceedings of the annual conference on taxation and minutes of the annual meeting of the National Tax Association, vol 96(2003), 91–104
Bobek DD, Hageman AM, Kelliher CF (2013) Analyzing the role of social norms in tax compliance behavior. J Bus Ethics 115(3):451–468CrossRef
Boone JP, Khurana IK, Raman KK (2013) Religiosity and tax avoidance. J Am Tax Assoc 35(1):53–84CrossRef
Castells M, Portes A (1989) World underneath: the origins, dynamics, and effects of the informal economy. In: Portes A, Castells M, Benton LA (eds) The informal economy; studies in advanced and less developed countries. The Johns Hopkins University Press, Baltimore
Chen MA, Vanek J, Carr M (2004) Mainstreaming informal employment and gender in poverty reduction: a handbook for policy-makers and other stakeholders. The Commonwealth Secretariat, London, United Kingdom
Chen MA (2012) The informal economy: definitions, theories and policies. WIEGO working paper no. 1. WIEGO
Clotfelter CT (1983) Tax evasion and tax rates: an analysis of individual returns. Rev Econ Stat 65(3):363–373CrossRef
Dabare R, Wai Wong K, Koutsakis P, Fairuz Shiratuddin M (2018) A study of the effect of dropout on imbalanced data classification using deep neural networks. J Multidiscip Eng Sci Technol (JMEST) 5(10):2458–9403
de Soto H (1989) The other path; the invisible revolution in the third world. Harper and Row, New York
Di Franco G, Santurro M (2021) Machine learning, artificial neural networks and social research. Qual Quant 55(3):1007–1025CrossRef
Dreher A, Kotsogiannis C, McCorriston S (2009) How do institutions affect corruption and the shadow economy? Int Tax Public Financ 16(6):773–796CrossRef
Dularif M, Sutrisno T, Nurkholis, & Saraswati, E. (2019) Is deterrence approach effective in combating tax evasion? A meta-analysis. Probl Perspect Manag 17(2):93–113
Elek P, Köllő J (2019) Eliciting permanent and transitory undeclared work from matched administrative and survey data. Empirica 46(3):547–576CrossRef
Engel C, Mittone L, Morreale A (2020) Tax morale and fairness in conflict an experiment. J Econ Psychol 81(March):102314CrossRef
European Commission (1998) Communication from the Commission on undeclared work (COM(1998) 219 Final)
European Commission (2019) Standard Eurobarometer 91. Public opinion in the European Union
Fegatilli E (2009) Undeclared work in the European Union. What can we learn from an European survey? Centre de Recherche En Economie Publique et de La Population, CREPP working paper 2009-02
Feld LP, Frey BS (2007) Tax compliance as the result of a psychological tax contract: the role of incentives and responsive regulation. Law Policy 29(1):102–120CrossRef
Feld LP, Larsen C (2012) Self-perceptions, government policies and tax compliance in Germany. Int Tax Public Financ 19(1):78–103CrossRef
Fernández Hilario A, García López S, Galar M, Prati RC, Krawczyk B, Herrera F (2018) Learning from imbalanced data sets. Springer, ChamCrossRef
Fields GS (1990) Labour market modelling and the urban informal sector: theory and evidence. In: Turnham D, Salomé B, Schwarz A (eds) The informal sector revisited. Organisation for Economic Co-operation and Development, Paris, pp 49–69
Forteza A, Noboa C (2019) Perceptions of institutional quality and justification of tax evasion. Const Polit Econ 30(4):367–382CrossRef
Franic J (2019) Explaining workers’ role in illegitimate wage underreporting practice: Evidence from the European Union. Econ Labour Relat Rev 30(3):366–381CrossRef
Franic J (2020a) Repression, voluntary compliance and undeclared work in a transition setting: some evidence from Poland. Post Communist Econ 32(2):250–266CrossRef
Franic J (2020b) Dissecting the illicit practice of wage underreporting: some evidence from Croatia. Econ Res 33(1):957–973MathSciNet
Franic J (2020c) Why workers engage in quasi-formal employment? Some lessons from Croatia. East J Eur Stud 11(2):94–112
Frey BS, Torgler B (2007) Tax morale and conditional cooperation. J Comp Econ 35(1):136–159CrossRef
Geertz C (1963) Peddlers and princes. The University of Chicago Press, Chicago
Genuer R, Poggi J-M (2020) Random forests with R. In Use R! Springer, BerlinCrossRef
Gërxhani K, Wintrobe R (2021) Understanding tax evasion: combining the public choice and new institutionalist perspectives. In: Douarin E, Havrylyshyn O (eds) The Palgrave handbook of comparative economics. Palgrave Macmillan, Cham, pp 785–810CrossRef
Ghoddusi H, Creamer GG, Rafizadeh N (2019) Machine learning in energy economics and finance: a review. Energy Econ 81:709–727CrossRef
Goel RK, Saunoris JW (2017) Unemployment and international shadow economy: gender differences. Appl Econ 49(58):5828–5840CrossRef
Gregorio, C. De, & Giordano, A. (2016). The heterogeneity of undeclared work in Italy: some results from the statistical integration of survey and administrative sources. Istituto nazionale di statistica.
Grimmer J, Roberts ME, Stewart BM (2021) Machine learning for social science: an agnostic approach. Annu Rev Polit Sci 24(1):395–419CrossRef
Hofmann E, Voracek M, Bock C, Kirchler E (2017) Tax compliance across sociodemographic categories: meta-analyses of survey studies in 111 countries. J Econ Psychol 62:63–71CrossRef
Horodnic IA, Williams CC (2019) Tackling undeclared work in the European Union: beyond the rational economic actor approach. Policy Stud 0(0):1–35
ILO (1972) Employment, incomes and equality; a strategy for increasing productive employment in Kenya. International Labour Organization, Geneva
ILO (1993) Statistics of employment in the informal sector. In: Fifteenth international conference of labour statisticians (fifteenth international conference of labour statisticians). International Labour Organization
ILO (2002) Decent work and informal economy. In: International labour conference report. International Labour Organization
Islam A, Rashid MHU, Hossain SZ, Hashmi R (2020) Public policies and tax evasion: evidence from SAARC countries. Heliyon 6(11):e05449CrossRef
Jimenez P, Iyer GS (2016) Tax compliance in a social setting: the influence of social norms, trust in government, and perceived fairness on taxpayer compliance. Adv Account 34:17–26CrossRef
Johnson JM, Khoshgoftaar TM (2019) Survey on deep learning with class imbalance. J Big Data 6(1):27
Kassa ET (2021) Factors influencing taxpayers to engage in tax evasion: evidence from Woldia City administration micro, small, and large enterprise taxpayers. J Innov Entrep 10(1):8
Kayaoglu A, Williams CC (2017) Beyond the declared/undeclared economy dualism: evaluating individual and country level variations in the prevalence of under-declared employment. J Econ Manag Perspect 11(4):36–47
Kemme DM, Parikh B, Steigner T (2020) Tax morale and international tax evasion. J World Bus 55(3):101052CrossRef
Khlif H, Guidara A, Hussainey K (2016) Sustainability level, corruption and tax evasion: a cross-country analysis. J Financ Crime 23(2):328–348CrossRef
Kogler C, Batrancea L, Nichita A, Pantya J, Belianin A, Kirchler E (2013) Trust and power as determinants of tax compliance: testing the assumptions of the slippery slope framework in Austria, Hungary, Romania and Russia. J Econ Psychol 34:169–180CrossRef
Kogler C, Muehlbacher S, Kirchler E (2015) Testing the “slippery slope framework” among self-employed taxpayers. Econ Gov 16(2):125–142CrossRef
Kuehn Z (2014) Tax rates, governance, and the informal economy in high-income countries. Econ Inq 52(1):405–430CrossRef
Lago-Peñas I, Lago-Peñas S (2010) The determinants of tax morale in comparative perspective: evidence from European countries. Eur J Polit Econ 26(4):441–453CrossRef
Lewis WA (1954) Economic development with unlimited supplies of labour. Manch Sch Econ Soc Stud 22(2):139–191CrossRef
Li D, Bledso JR, Zeng Y, Liu W, Hu Y, Bi K, Liang A, Li S (2020) A deep learning diagnostic platform for diffuse large B-cell lymphoma with high accuracy across multiple hospitals. Nat Commun 11(1):6004
Li L, Ma G (2015) Government size and tax evasion: evidence from China. Pac Econ Rev 20(2):346–364CrossRef
McKay S (2014) Transnational aspects of undeclared work and the role of EU Legislation. Eur Labour Law J 5(2):116–131MathSciNetCrossRef
Mitchell TM (1997) Machine learning. McGraw-Hill, New York
Molina M, Garip F (2019) Machine learning for sociology. Ann Rev Sociol 45:27–45CrossRef
Moser CON (1978) Informal sector or petty commodity production: dualism or dependence in urban development? World Dev 6(9/10):1041–1064CrossRef
Mullainathan S, Spiess J (2017) Machine learning: an applied econometric approach. J Econ Perspect 31(2):87–106CrossRef
Palumbo L (2017) Exploiting for care: trafficking and abuse in domestic work in Italy. J Immigr Refug Stud 15(2):171–186CrossRef
Peattie L (1987) An idea in good currency and how it grew: the informal sector. World Dev 15(7):851–860CrossRef
Pfau-Effinger B (2009) Varieties of undeclared work in European societies. Br J Ind Relat 47(1):79–99CrossRef
Picur RD, Riahi-Belkaoui A (2006) The impact of bureaucracy, corruption and tax compliance. Rev Acc Financ 5(2):174–180CrossRef
Pommerehne WW (1996) Tax rates, tax administration and income tax evasion in Switzerland. Public Choice 88(1–2):161–170CrossRef
Popescu ME, Cristescu A, Stanila L, Vasilescu MD (2016) Determinants of undeclared work in the EU member states. Procedia Econ Financ 39:520–525CrossRef
Popescu GH, Davidescu AAM, Huidumac C (2018) Researching the main causes of the romanian shadow economy at the micro and macro levels: Implications for sustainable development. Sustainability (switzerland) 10(10):3518CrossRef
Portes A, Sassen-Koob S (1987) Making it underground: comparative material on the informal sector in western market economies. Am J Sociol 93(1):30–61CrossRef
Porthé V, Ahonen E, Vázquez ML, Pope C, Agudelo AA, García AM, Amable M, Benavides FG, Benach J (2010) Extending a model of precarious employment: a qualitative study of immigrant workers in Spain. Am J Ind Med 53(4):417–424CrossRef
Rakowski CA (1994) Convergence and divergence in the informal sector debate: a focus on Latin America, 1984–92. World Dev 22(4):501–516CrossRef
Rashid HU, Buhayan SA, Masud AK, Sawyer A (2021) Impact of governance quality and religiosity on tax evasion: evidence from OECD countries. Adv Tax 29:89–110CrossRef
Rei D, Bhattacharya M (2008) The impact of institutions and policy on informal economy in developing countries. An econometric exploration. Working paper no. 84. International Labour Organization (ILO)
Riahi-Belkaoui A (2004) Relationship between tax compliance internationally and selected determinants of tax morale. J Int Account Audit Tax 13(2):135–143CrossRef
Richardson G (2006) Determinants of tax evasion: a cross-country investigation. J Int Account Audit Tax 15(2):150–169CrossRef
Rodgers P, Shahid MS, Williams CC (2019) Reconceptualizing informal work practices: some observations from an ethnic minority community in urban UK. Int J Urban Reg Res 43(3):476–496CrossRef
Rodrigues MJS (2020). Power and trust as determinants of tax compliance. The slippery slope framework applied to Portugal and Switzerland. Master thesis. Lisbon School of Economics and Management
Sethuraman SV (1976) The urban informal sector: concept, measurement and policy. Int Labour Rev 114(1):69–81
Shafer WE, Wang Z, Hsieh TS (2020) Support for economic inequality and tax evasion. Sustainability 12(19):1–18CrossRef
Strielkowski W, Čábelková I (2015) Religion, culture, and tax evasion: evidence from the Czech Republic. Religions 6(2):657–669CrossRef
Tokman VE (1978) An exploration into the nature of informal—formal sector relationship. World Dev 6(9/10):1065–1075CrossRef
Torgler B (2004) Tax morale, trust and corruption: empirical evidence from transition countries. Center for Research in Economics, Management and the Arts, Working paper no. 2004–05
Vallanti G, Gianfreda G (2020) Informality, regulation and productivity: do small firms escape EPL through shadow employment? Small Bus Econ 57:1383–1412CrossRef
van Dijke M, Verboon P (2010) Trust in authorities as a boundary condition to procedural fairness effects on tax compliance. J Econ Psychol 31(1):80–91CrossRef
Vorley T, Williams C (2012) Evaluating the variations in undeclared work in the European Union. J Econ Appl 2(2):20–39
Williams CC (2004) Cash-in-hand work; the underground sector and the hidden economy of favours. Palgrave Macmillan, Cham
Williams CC (2007) Tackling undeclared work in Europe: lessons from a study of Ukraine. Eur J Ind Relat 13(2):219–236CrossRef
Williams CC (2015) Explaining the informal economy: an exploratory evaluation of competing perspectives. Relat Ind 70(4):741–765
Williams CC (2019) Explaining and tackling the informal economy: an evaluation of competing perspectives. Open Econ 2:63–75CrossRef
Williams CC, Bezeredi S (2017) Tackling the illegal practice of under-reporting employees’ wages: lessons from the Republic of Macedonia. UTMS J Econ 8(3):243–258
Williams CC, Efendic AS (2020) Evaluating the relationship between migration and participation in undeclared work: lessons from Bosnia and Herzegovina. Econ Altern 26(4):592–606CrossRef
Williams CC, Efendic A (2021) Evaluating the relationship between marginalization and participation in undeclared work: lessons from Bosnia and Herzegovina. Southeast Eur Black Sea Stud 00(00):1–19
Williams CC, Horodnic IA (2015b) Who participates in the undeclared economy in South-Eastern Europe? An evaluation of the marginalization thesis. South Eastern Europe J Econ 13(2):157–175
Williams CC, Horodnic IA (2016) Evaluating the illegal employer practice of under-reporting employees’ salaries. Br J Ind Relat 55(1):1–29
Williams CC, Horodnic IA (2017a) Tackling bogus self-employment: some lessons from Romania. J Dev Entrep 22(2):1–20
Williams CC, Horodnic IA (2017b) Who participates in undeclared work in the European Union? Toward a reinforced marginalization perspective. Int J Sociol 47(2):99–115CrossRef
Williams CC, Öz-Yalaman G (2021) Re-theorising participation in undeclared work in the European Union: lessons from a 2019 Eurobarometer survey. Eur Soc 1(1):1–25
Williams CC, Round J (2007) Re-thinking the nature of the informal economy: some lessons from Ukraine. Int J Urban Reg Res 31(2):425–441CrossRef
Williams CC, Yang J (2018) Evaluating competing perspectives towards undeclared work: some lessons from Bulgaria. J Contemp Cent East Europe 26(2–3):247–265CrossRef
Williams CC, Horodnic IA, Windebank J (2015a) Evaluating the prevalence and distribution of envelope wages in the European Union: lessons from a 2013 Eurobarometer survey. J Contemp Eur Res 11(2):179–195CrossRef
Williams CC, Horodnic IA, Windebank J (2015b) Explaining participation in the informal economy: an institutional incongruence perspective. Int Sociol 30(3):294–313CrossRef
Windebank JE, Horodnic IA (2017) Explaining participation in undeclared work in France: lessons for policy evaluation. Int J Sociol Soc Policy 37(3/4):203–217CrossRef
Wyner AJ, Olson M, Bleich J, Mease D (2017) Explaining the success of adaboost and random forests as interpolating classifiers. J Mach Learn Res 18:1–33MathSciNet
Yamen A, Allam A, Bani-Mustafa A, Uyar A (2018) Impact of institutional environment quality on tax evasion: a comparative investigation of old versus new EU members. J Int Account Audit Tax 32:17–29CrossRef
Yitzhaki S (1987) On the excess burden of tax evasin. Public Financ Q 15(2):123–137CrossRef
Metadata
Title
What do we really know about the drivers of undeclared work? An evaluation of the current state of affairs using machine learning
Author
Josip Franic
Publication date
23-06-2022
Publisher
Springer London
Published in
AI & SOCIETY / Issue 2/2024
Print ISSN: 0951-5666
Electronic ISSN: 1435-5655
DOI
https://doi.org/10.1007/s00146-022-01490-3

Other articles of this Issue 2/2024

AI & SOCIETY 2/2024 Go to the issue

Curmudgeon Corner

Rules for privately owned robots in public spaces

Open Forum

Reading vs. Scanning: Notes on Re:Print

Editorial

Eliza and the artist

Original Paper

Are AI systems biased against the poor? A machine learning analysis using Word2Vec and GloVe embeddings

Curmudgeon Corner

The misdirected approach of open source algorithms

OPEN FORUM

‘Digitalising a National Archive’: interview with John Sheridan, Digital Director at The National Archives, UK

Premium Partner

    Image Credits