Abstract
The purpose of this study is to analyze tobacco spending in Georgia using various machine learning methods applied to a sample of 10,757 households from the Integrated Household Survey collected by GeoStat in 2016. Previous research has shown that smoking is the leading cause of death for 35–69 year olds. In addition, tobacco expenditures may constitute as much as 17% of the household budget. Five different algorithms (ordinary least squares, random forest, two gradient boosting methods and deep learning) were applied to 8,173 households (or 76.0%) in the train set. Out-of-sample predictions were then obtained for 2,584 remaining households in the test set. Under the default settings, a random forest algorithm showed the best performance with more than 10% improvement in terms of root-mean-square error (RMSE). Improved accuracy and availability of machine learning tools in R calls for active use of these methods by policy makers and scientists in health economics, public health and related fields.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Georgian government implemented/increased excise taxes on tobacco products in September 2013, January 2015 and July 2015. As of May of 2018, Georgia has introduced ban on public smoking of tobacco, including electronic cigarettes and Hookah.
- 2.
Data are publicly available at http://www.geostat.ge/index.php?action=meurneoba&mpid=1&lang=eng.
- 3.
Row tobacco used for pipe and hand rolling.
- 4.
For details refer to http://h2o-release.s3.amazonaws.com/h2o/master/3888/docs-website/h2o-docs/automl.html.
References
Bakhturidze, G., Peikrishvili, N., Mittelmark, M.: The influence of public opinion on tobacco control policy-making in Georgia: perspectives of governmental and non-governmental stakeholders. Public participation in tobacco control policy-making in Georgia. Tob. Prev. Cessat. 2(1), 1 (2016)
Block, S., Webb, P.: Up in smoke: tobacco use, expenditure on food, and child malnutrition in developing countries. Econ. Dev. Cult. Chang. 58(1), 1–23 (2009)
Berg, C.J., Topuridze, M., Maglakelidze, N., Starua, L., Shishniashvili, M., Kegler, M.C.: Reactions to smoke-free public policies and smoke-free home policies in the Republic of Georgia: results from a 2014 national survey. Int. J. Public Health 61(4), 409–416 (2016)
de Beyer, J., Lovelace, C., Yürekli, A.: Cover essay: poverty and tobacco. Tob. Control 10(3), 210–211 (2001)
Breiman, L.: Random forests. Mach. Learn. 45(1), 5–32 (2001)
Busch, S., Jofre-Bonet, M., Falba, T., Sindelar, J.: Burning a hole in the budget: tobacco spending and its crowd-out of other goods. Appl. Health Econ. Health Policy 3(4), 263–272 (2004)
Chen T., He T., Benesty M., Khotilovich V., Tang Y.: xgboost: EXTREME Gradient Boosting. R package version 0.6.4.1. https://CRAN.R-project.org/package=xgboost (2018)
Djibuti, M., Gotsadze, G., Mataradze, G., Zoidze, A.: Influence of household demographic and socio-economic factors on household expenditure on tobacco in six New Independent States. BMC Public Health 7(1), 222 (2007)
Efroymson, D., Ahmed, S., Townsend, J., Alam, S.M., Dey, A.R., Saha, R., Dhar, B., Sujon, A.I., Ahmed, K.U., Rahman, O.: Hungry for tobacco: an analysis of the economic impact of tobacco consumption on the poor in Bangladesh. Tob. Control 10, 212–217 (2001)
Efroymson, D., Pham, H.A., Jones, L., FitzGerald, S., Le Thuand, T., Le Hien, T.T.: Tobacco and poverty: evidence from Vietnam. Tob. Control 20(4), 296–301 (2011)
Gong, Y.L., Koplan, J.P., Feng, W., Chen, C.H., Zheng, P., Harris, J.R.: Cigarette smoking in China: prevalence, characteristics, and attitudes in Minhang District. JAMA 274(15), 1232–1234 (1995)
The H2O.ai Team: h2o: R Interface for H2O. R package version 3.16.0.2. (2017). https://CRAN.R-project.org/package=h2o
Johnson, R., Wang, M.Q., Smith, M., Connolly, G.: The association between parental smoking and the diet quality of low-income children. Pediatrics 97(3), 312–317 (1996)
Peto, R., Boreham, J., Lopez, A.D., Thun, M., Heath, C.: Mortality from tobacco in developed countries: indirect estimation from national vital statistics. Lancet 339(8804), 1268–1278 (1992)
Roberts, B., Gilmore, A., Stickley, A., Rotman, D., Prohoda, V., Haerpfer, C., McKee, M.: Changes in smoking prevalence in 8 countries of the former Soviet Union between 2001 and 2010. Am. J. Public Health 102(7), 1320–1328 (2012)
Torosyan K., Pignatti N., Obrizan M.: Job Market Outcomes of IDPs: The Case of Georgia. IZA DP No. 11301 (2018)
Wang, H., Sindelar, J.L., Busch, S.H.: The impact of tobacco expenditure on household consumption patterns in rural China. Soc. Sci. Med. 62(6), 1414–1426 (2006)
Xin, Y., Qian, J., Xu, L., Tang, S., Gao, J., Critchley, J.A.: The impact of smoking and quitting on household expenditure patterns and medical care costs in China. Tob. Control 18(2), 150–155 (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Obrizan, M., Torosyan, K., Pignatti, N. (2019). Tobacco Spending in Georgia: Machine Learning Approach. In: Chertov, O., Mylovanov, T., Kondratenko, Y., Kacprzyk, J., Kreinovich, V., Stefanuk, V. (eds) Recent Developments in Data Science and Intelligent Analysis of Information. ICDSIAI 2018. Advances in Intelligent Systems and Computing, vol 836. Springer, Cham. https://doi.org/10.1007/978-3-319-97885-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-97885-7_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97884-0
Online ISBN: 978-3-319-97885-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)