Subject. The article explores possibilities of using machine learning methods to assess the impact of education. Objectives. The purpose is to assess the impact of the level and profile of education using data of the Russia Longitudinal Monitoring Survey – Higher School of Economics (RLMS-HSE) and machine learning methods. Methods. Linear and logistic regression, k-nearest neighbors algorythm, support vectors, decision trees, random forest, boosting, and fully connected neural networks are used to predict wages, job satisfaction, and unemployment risk. Gender, age, region of residence, level and profile of education are used as explanatory variables. Results. The peak of salaries in the Russian labor market is achieved at a relatively young age. The highest salary premium for men is provided by higher education in the field of medicine and information technology, for women – in the field of medicine. The most job satisfaction among men with higher education is experienced by IT and medical graduates, among women – by graduates of pedagogical and agricultural profiles. Conclusions. The use of machine learning methods did not significantly improve the estimates of the impact of the level and profile of education obtained under the J. Mintzer model, although the boosting models showed a lower standard deviation in the test sample compared with the forecasts of regression models. When building financial models focused on comparing the cost of education with the increase in income from work, machine learning models are preferable due to higher accuracy of forecasts.
Keywords: return on education, human capital, job satisfaction, machine learning, decision tree
References:
Schultz T.W. Economic Value of Education. London, New York, Columbia University Press, 1963, 92 p.
Becker G.S. Human Capital: A Theoretical and Empirical Analysis with Special Reference to Education. London, New York, Columbia University Press, 1964, 390 p.
Becker G.S., Chiswick B. Education and the distribution of earnings. The American Economic Review, 1966, vol. 56, no. 1/2, pp. 358–369. URL: Link
Mincer J.A. Investment in human capital and personal income distribution. Journal of Political Economy, 1958, vol. 66, no. 4, pp. 281–302. URL: Link
Mincer J.A. Schooling, Experience, and Earnings. N.Y., NBER Books, 1974, 152 p.
Goldin C., Katz L.F. The race between education and technology: The evolution of US educational wage differentials, 1890 to 2005. NBER Working Paper, 2007, no. 12984. URL: Link
Luk'yanova A.L. [Returns to Education in Russia: Evidence from Meta-Analysis]. Ekonomicheskii zhurnal Vysshei shkoly ekonomiki = The HSE Economic Journal, 2010, vol. 14, no. 3, pp. 326–348. URL: Link (In Russ.)
Denisova I.A., Kartseva M.A. Preimushchestva inzhenernogo obrazovaniya: otsenka otdachi na obrazovatel'nye spetsial'nosti v Rossii. Preprint WP3/2005/02 [Advantages of engineering education: Assessment of the impact on educational specialties in Russia. Preprint WP3/2005/02]. Moscow, HSE Publ., 2005, 40 p. (In Russ.)
Antonenko V.V., Antonov G.V. [Investing in the Russian youth human capital: Who benefits?]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2016, no. 3, pp. 96–110. URL: Link (In Russ.)
Antonenko V.V., Antonov G.V. [A statistical model of dependence of income on educational level in modern-day Russia]. Regional'naya ekonomika: teoriya i praktika = Regional Economics: Theory and Practice, 2018, vol. 16, iss. 12, pp. 2349–2368. (In Russ.) URL: Link
Gimpel'son V.E. [Age and Wage: Stylized Facts and Russian Evidence]. Ekonomicheskii zhurnal Vysshei shkoly ekonomiki = The HSE Economic Journal, 2019, vol. 23, no. 2, pp. 185–237. URL: Link (In Russ.)
Gimpel'son V.E., Zinchenko D.I. [“Physicists” and “lyricists”: Whom the Russian labor market values higher?]. Voprosy Ekonomiki, 2021, no. 8, pp. 5–36. (In Russ.) URL: Link
Kapelyushnikov R.I. [Returns to education in Russia: Nowhere below?]. Voprosy Ekonomiki, 2021, no. 8, pp. 37–68. (In Russ.) URL: Link
Arteeva V.S., Skhvediani A.E. [A mathematical model to evaluate return on investment in higher education]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2021, vol. 20, iss. 4, pp. 772–788. (In Russ.) URL: Link
Rozhkova K.V., Roshchin S.Yu., Solntsev S.A., Travkin P.V. [The return to master’s degree in the Russian labor market]. Voprosy Ekonomiki, 2021, no. 8, pp. 69–92. (In Russ.) URL: Link
Mel'nikov R.M. [Estimation of return on investment of Master's degree in Russian conditions]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2022, vol. 21, iss. 4, pp. 665–689. (In Russ.) URL: Link
Mel'nikov R.M. [Evaluating the return on investment in postgraduate research training under modern conditions in Russia]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2017, vol. 16, iss. 3, pp. 444–459. (In Russ.) URL: Link
Breiman L., Friedman J., Stone Ch., Olshen R. Classification and Regression Trees. Taylor and Francis, 1984, 368 p.
Hastie T., Tibshirani R., Friedman J. The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Springer, 2009, 745 p.
Ozdemir S. Principles of Data Science. Birmingham, UK, Packt Publishing Ltd, 2016, 388 p.
Dangeti P. Statistics for Machine Learning: Techniques for Exploring Supervised, Unsupervised, and Reinforcement Learning Models with Python and R. Birmingham, UK, Packt Publishing Ltd, 2017, 442 p.
James G., Witten D., Hastie T. et al. An Introduction to Statistical Learning: With Applications in Python. Springer, 2023, 619 p.
Teguim Kamdjou H.D. Estimating the returns to education using a machine learning approach – Evidence for different regions. Open Education Studies, 2023, vol. 5, iss. 1. URL: Link
Jacob J. Human capital and higher education: Rate of returns across disciplines. Economics Bulletin, 2018, vol. 38, iss. 2, pp. 1241–1256. URL: Link
