BazEkon - Biblioteka Główna Uniwersytetu Ekonomicznego w Krakowie

BazEkon home page

Meny główne

Autor
Kuryłek Wojciech (University of Warsaw)
Tytuł
Is the Inclusion of a Broad Set of Explanatory Variables Relevant in EPS Forecasting? Evidence from Poland
Czy uwzględnienie szerokiego zestawu zmiennych objaśniających jest istotne w prognozowaniu EPS? Dowody z Polski
Źródło
Bank i Kredyt, 2025, nr 3, s. 339-360, aneks, bibliogr. s. 350-354
Bank & Credit
Słowa kluczowe
Zysk na akcję, Drzewo decyzyjne, Rynki finansowe
Earnings per Share (EPS), Decision tree, Financial markets
Uwagi
streszcz., summ.
Firma/Organizacja
Giełda Papierów Wartościowych w Warszawie
Warsaw Stock Exchange
Abstrakt
W niniejszym artykule zbadano rolę dokładnych prognoz zysków spółek notowanych na giełdzie-kluczową w osiąganiu sukcesu inwestycyjnego, szczególnie na rynkach o ograniczonym pokryciu prognozami przez analityków, takich jak rynki wschodzące, m.in. w Polsce. Podczas gdy analitycy finansowi szeroko prognozują wyniki finansowe spółek na rozwiniętych rynkach, takich jak USA, jedynie niewielka część firm (około 20%) cieszy się podobnym zainteresowaniem w Polsce. Istnieje obszerna literatura poświęcona prognozowaniu zysków na akcję, głównie w USA, choć wyniki tych badań są zróżnicowane. W artykule oceniono dokładność prognoz generowanych przez szeroką gamę zmiennych objaśniających, w tym zmienne księgowe, rynkowe i makroekonomiczne, wykorzystując uczenie maszynowe oparte na drzewach decyzyjnych ze wzmocnieniem gradientowym, wielowarstwowych sieciach perceptronowych i sieciach konwolucyjnych, w porównaniu z sezonowym modelem spaceru losowego. Modele te zastosowano w odniesieniu do danych EPS spółek notowanych na Giełdzie Papierów Wartościowych w latach 2008-2019. W zastosowanych metodach wielowymiarowych wykorzystano kompleksowy zestaw 1598 zmiennych objaśniających, obejmujących specyficzne dla spółki wskaźniki finansowe i rynkowe wraz ze wskaźnikami makroekonomicznymi. Model sezonowego błądzenia losowego wykazał najniższy błąd mierzony za pomocą średniego bezwzględnego błędu arcus tangensa (MAAPE), czego wyniki potwierdzono testami statystycznymi. Liczne kontrole stabilności wyników, obejmujące różne ramy czasowe i wskaźniki błędów, potwierdzają ten wynik. Dominacja modelu uproszczonego może wynikać z tendencji do nadmiernego dopasowania modeli złożonych oraz stosunkowo prostej dynamiki obserwowanej w polskich spółkach giełdowych. (abstrakt oryginalny)

This study explores the critical role of accurate earnings forecasts for publicly traded firms in achieving investment success, particularly in markets with limited analyst coverage, such as emerging markets like Poland. It evaluates the precision of forecasts generated by a wide array of explanatory variables, including accounting, market, and macroeconomic factors, employing gradient-boosting decision tree machine learning, multilayer perceptron networks, and convolution networks, contrasted with a seasonal random walk model. These models are applied to EPS data from companies listed on the Warsaw Stock Exchange from 2008 to 2019. Multivariate methods are trained using a comprehensive set of 1,598 explanatory variables, encompassing company-specific financial and market metrics along with macroeconomic indicators. The seasonal random walk model demonstrated the lowest error, as measured by the Mean Arctangent Absolute Percentage Error (MAAPE), findings validated through rigorous statistical examinations. Various robustness checks, employing diverse timeframes and error metrics, reaffirm this outcome. The dominance of a simplistic model may arise from the overfitting tendencies of complex models and the relatively straightforward dynamics observed in Polish listed companies. (original abstract)
Dostępne w
Biblioteka Główna Uniwersytetu Ekonomicznego w Katowicach
Pełny tekst
Pokaż
Bibliografia
Pokaż
  1. Abarbanell J., Bushee B. (1997), Fundamental analysis, future EPS, and stock prices, Journal of Accounting Research, 35(1), 1-24, DOI: 10.2307/2491464.
  2. Ahmadpour A., Etemadi H., Moshashaei S. (2015), Earnings per share forecast using extracted rules from trained neural network by genetic algorithm, Computational Economics, 46(1), 55-63, DOI: 10.1007/s10614-014-9455-6.
  3. Atiya A., Shaheen S., Talaat N. (1997), An efficient stock market forecasting model using neural networks, IEEE International Conference on Neural Networks, DOI: 10.1109/ICNN.1997.614231.
  4. Ball R., Ghysels E. (2017), Automated earnings forecasts: beat analysts or combine and conquer?, Management Science, 64(10), 4936-4952, DOI: 10.1287/mnsc.2017.2864.
  5. Ball R., Watts R. (1972), Some time series properties of accounting income, The Journal of Finance, 27(3), 663-681, DOI: 10.1111/j.1540-6261.1972.tb00991.x.
  6. Banerjee P. (2020), A guide on XGBoost hyperparameters tuning, https://www.kaggle.com/code/ prashant111/a-guide-on-xgboost-hyperparameters-tuning.
  7. Bansal N., Nasseh A., Strauss J. (2015), Can we consistently forecast a firm's earnings? Using combination forecast methods to predict the EPS of Dow firms, Journal of Economics and Finance, 39(1), 1-22, DOI: 10.1007/s12197-012-9234-y.
  8. Bathke Jr. A.W., Lorek K.S. (1984), The relationship between time-series models and the security market's expectation of quarterly earnings, The Accounting Review, 59(2), 163-176.
  9. Bradshaw M., Drake M., Myers J., Myers L. (2012), A re-examination of analysts' superiority over time-series forecasts of annual earnings, Review of Accounting Studies, 17(4), 944-968, DOI: 10.1007/ s11142-012-9185-8.
  10. Bengio Y., Courville A., Goodfellow I. (2017), Deep Learning, The MIT Press.
  11. Bengio Y., Glorot X. (2010), Understanding the difficulty of training deep feedforward neural networks, 13th International Conference on Artificial Intelligence and Statistics, 9, 249-256.
  12. Brandon Ch., Jarrett J.E., Khumawala S.B. (1987), A comparative study of the forecasting accuracy of Holt-Winters and economic indicator models of earnings per share for financial decision making, Managerial Finance, 13(2), 10-15, DOI: 10.1108/eb013581.
  13. Brooks L.D., Buckmaster D.A. (1976), Further evidence of the time series properties of accounting income, The Journal of Finance, 31(5), 1359-1373, DOI: 10.1111/j.1540-6261.1976.tb03218.x.
  14. Brown L.D., Griffin P.A., Hagerman R.L., Żmijewski M.E. (1987), Security analyst superiority relative to univariate time-series models in forecasting quarterly earnings, Journal of Accounting and Economics, 9(1), 61-87, DOI: 10.1016/0165-4101(87)90017-6.
  15. Brown L.D., Rozeff M.S. (1979), Univariate time-series models of quarterly accounting earnings per share: a proposed model, Journal of Accounting Research, 17(1), 179-189, DOI: 10.2307/2490312.
  16. Cao Q., Gan Q. (2009), Forecasting EPS of Chinese listed companies using a neural network with genetic algorithm, 15th Americas Conference on Information Systems, AMCIS 2009, 2791-2981.
  17. Cao Q., Parry M. (2009), Neural network earnings per share forecasting models: a comparison of backward propagation and the genetic algorithm, Decision Support Systems, 47(1), 32-41, DOI: 10.1016/j.dss.2008.12.011.
  18. Cao Q., Schniederjans M.J., Zhang W. (2004), Neural network earnings per share forecasting models: a comparative analysis of alternative methods, Decision Sciences, 35(2), 205-237, DOI: 10.1111/ j.00117315.2004.02674.x.
  19. Chant P.D. (1980), On the predictability of corporate earnings per share behavior, The Journal of Finance, 35(1), 13-21, DOI: 10.2307/2327177.
  20. Chen Y., Chen S., Huang H., Sangaiah A. (2020), Applied identification of industry data science using an advanced multi-componential discretization model, Symmetry, 12(10), 1-28, DOI: 10.3390/ sym12101620.
  21. Chen T., Guestrin C. (2016), XGBoost: a scalable tree boosting system, 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785-794, DOI: 10.1145/2939672.2939785.
  22. Conroy R., Harris R. (1987), Consensus forecasts of corporate earnings: analysts' forecasts and time series methods, Management Science, 33(6), 725-738, DOI: 10.1287/mnsc.33.6.725.
  23. Delen D., Kuzey C., Uyar A. (2013), Measuring firm performance using financial ratios: a decision tree approach, Expert Systems with Applications, 40(10), 3970-3983, DOI: 10.1016/j.eswa.2013.01.012.
  24. Dreher S., Eichfelder S., Noth F. (2024), Does IFRS information on tax loss carryforwards and negative performance improve predictions of earnings and cash flows?, Journal of Business Economics, 94(1), 1-39, DOI: 10.1007/s11573-023-01147-7.
  25. Elamir E. (2020), Modeling and predicting earnings per share via regression tree approaches in banking sector: Middle East and North African countries case, Investment Management and Financial Innovations, 17(2), 51-68, DOI: 10.21511/imfi.17(2).2020.05.
  26. Elend L., Kramer O., Lopatta K., Tideman S. (2020), Earnings prediction with deep learning, KI 2020: Advances in Artificial Intelligence, 267-274, DOI: 10.1007/978-3-030-58285-2_22.
  27. Elton E.J., Gruber M.J. (1972), Earnings estimates and the accuracy of expectational data, Management Science, 18(8), B409-B424, DOI: 10.1287/mnsc.18.8.B409.
  28. Foster G. (1977), Quarterly accounting data: time-series properties and predictive-ability results, The Accounting Review, 52(1), 1-21.
  29. Fukushima K. (1980), Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biological Cybernetics, 36(4), 193-202, DOI: 10.1007/BF00344251.
  30. Gabbouj M., Iosifidis A., Kanniainen J., Passalis N., Tefas A., Tsantekidis A. (2017), Forecasting stock prices from the limit order book using convolutional neural networks, IEEE 19th conference on business informatics (CBI), DOI: 10.1109/cbi.2017.23.
  31. Gaio L., Gatsios R., Lima F., Piamenta Jr. T. (2021), Re-examining analyst superiority in forecasting results of publicly-traded Brazilian companies, Revista de Administracao Mackenzie, 22(1), eRAMF210164, DOI: 10.1590/1678-6971/eramf210164.
  32. Gramacy R.B., Gerakos J. (2013), Regression-based earnings forecasts, Chicago Booth Research Paper, 12-26, DOI: 10.2139/ssrn.2112137.
  33. Griffin P. (1977), The time-series behavior of quarterly earnings: preliminary evidence, Journal of Accounting Research, 15(1), 71-83, DOI: 10.2307/2490556.
  34. Gupta R., Khirbat G., Singh S. (2013), Optimal neural network architecture for stock market forecasting, 2013 International Conference on Communication Systems and Network Technologies, 557-561, DOI: 10.1109/csnt.2013.120.
  35. Harris R.D.F., Wang P. (2019), Model-based earnings forecasts vs. financial analysts' earnings forecasts, British Accounting Review, 51(4), 424-437, DOI: 10.1016/j.bar.2018.10.002.
  36. Heaton J. (2008), Introduction to Neural Networks for Java, Heaton Research Inc.
  37. Hou K., van Dijk M., Zhang Y. (2012), The implied cost of capital: a new approach, Journal of Accounting and Economics, 53(3), 504-526, DOI: 10.1016/j.jacceco.2011.12.001.
  38. Jarrett J.E. (2008), Evaluating methods for forecasting earnings per share, Managerial Finance, 16, 30-35, DOI: 10.1108/eb013647.
  39. Johnson T.E., Schmitt T.G. (1974), Effectiveness of earnings per share forecasts, Financial Management, 3(2), 64-72, DOI: 10.2307/3665292.
  40. Kim S., Kim H. (2016), A new metric of absolute percentage error for intermittent demand forecasts, International Journal of Forecasting, 32(3), 669-679, DOI: 10.1016/j.ijforecast.2015.12.003.
  41. Kuryłek W. (2023a), The modeling of earnings per share of Polish companies for the post-financial crisis period using random walk and ARIMA models, Journal of Banking and Financial Economics, 1(19), 26-43, DOI: 10.7172/2353-6845.jbfe.2023.1.2.
  42. Kuryłek W. (2023b), Can exponential smoothing do better than seasonal random walk for earnings per share forecasting in Poland?, Bank i Kredyt, 54(6), 651-672.
  43. Kuryłek W. (2024), Can we profit from BigTechs' time series models in predicting earnings per share? Evidence from Poland, Data Science in Finance and Economics, 4(2), 218-235, DOI: 10.3934 DSFE.2024008.
  44. Lacina M., Lee B., Xu R. (2011), An evaluation of financial analysts and naïve methods in forecasting long-term earnings, in: K.D. Lawrence, R.K. Klimberg (eds.), Advances in Business and Management Forecasting, Emerald Publishing, DOI: 10.1108/S1477-4070(2011)0000008009.
  45. Lai S., Li H. (2006), The predictive power of quarterly earnings per share based on time series and artificial intelligence model, Applied Financial Economics, 16(18), 1375-1388, DOI: 10.1080/ 09603100600592752.
  46. Lev B. (1980), On the use of index models in analytical reviews by auditors, Journal of Accounting Research, 18(2), 524-550, DOI: 10.2307/2490591.
  47. Lev B., Souginannis T. (2010), The usefulness of accounting estimates for predicting cash flows and earnings, Review of Accounting Studies, 15(4), 779-807, DOI: 10.1007/s11142-009-9107-6.
  48. Lev B., Thiagarajan S. (1993), Fundamental information analysis, Journal of Accounting Research, 31(2), 190-215, DOI: 10.2307/2491270.
  49. Li K.K. (2011), How well do investors understand loss persistence?, Review of Accounting Studies, 16(3), 630-667, DOI: 10.1007/s11142-011-9157-4.
  50. Li K.K., Mohanram P. (2014), Evaluating cross-sectional forecasting models for the implied cost of capital, Review of Accounting Studies, 19(3), 1152-1185, DOI: 10.1007/s11142-014-9282-y.
  51. Lorek K.S. (1979), Predicting annual net earnings with quarterly earnings time-series models, Journal of Accounting Research, 17(1), 190-204, DOI: 10.2307/2490313.
  52. Lorek K.S, Willinger G.L. (1996), A multivariate time-series model for cash-flow data, Accounting Review, 71, 81-101.
  53. Ohlson J.A. (1995), Earnings, book values, and dividends in equity valuation, Contemporary Accounting Research, 11(2), 661-687, DOI: 10.1092/7tpj-rxqn-tqc7-ffae.
  54. Ohlson J.A. (2001), Earnings, book values, and dividends in equity valuation: an empirical perspective, Contemporary Accounting Research, 18(1), 107-120, DOI: 10.1092/7tpj-rxqn-tqc7-ffae.
  55. Ohlson J.A., Juettner-Nauroth B.E. (2005), Expected EPS and EPS growth as determinants of value, Review of Accounting Studies, 10(2-3), 349-365, DOI: 10.1007/s11142-005-1535-3.
  56. Pagach D.P., Warr R.S. (2020), Analysts versus time-series forecasts of quarterly earnings: a maintained hypothesis revisited, Advances in Accounting, 51, 1-15, DOI: 10.1016/j.adiac.2020.100497.
  57. Pasini A. (2015), Artificial neural networks for small dataset analysis, Journal of Thoracic Disease, 7(5), 953-960.
  58. Pope P.F., Wang P. (2005), Earnings components, accounting bias and equity valuation, Review of Accounting Studies, 10(4), 387-407, DOI: 10.1007/s11142-005-4207-4.
  59. Pope P., Wang P. (2014), On the relevance of earnings components: valuation and forecasting links, Review of Quantitative Finance and Accounting, 42, 399-413, DOI: 10.1007/s11156-013-0347-y.
  60. Rosenblatt F. (1958), The perceptron: a probabilistic model for information storage and organization in the brain, Psychological Review, 65(6), 386-408, DOI: 10.1037/h0042519.
  61. Ruland W. (1980), On the choice of simple extrapolative model forecasts of annual earnings, Financial Management, 9(2), 30-37, DOI: 10.2307/3665165.
  62. Simon J. (2020), Learn Amazon SageMaker: A guide to building, training, and deploying machine learning models for developers and data scientists, Packt.
  63. Suler P., Vochozka M., Vrbka J. (2020), Bankruptcy or success? The effective prediction of a company's financial development using LSTM, Sustainability, 12(18), 2299-2314, DOI: 10.3390/su12187529.
  64. Watts R.L. (1975), The time series behavior of quarterly earnings, Working Paper, April, University of New Castle.
  65. Werbos P. (1988), Backpropagation: past and future, IEEE International Conference on Neural Networks, 343-353, DOI: 10.1109/ICNN.1988.23866.
  66. Wilcoxon F. (1945), Individual comparisons by ranking methods, Biometrics, 1, 80-83, DOI: 10.2307/ 3001968.
  67. Xiaoqiang W. (2022), Research on enterprise financial performance evaluation method based on data mining, 2022 IEEE 2nd International Conference on Electronic Technology, Communication and Information (ICETCI), DOI: 10.1109/icetci55101.2022.9832404.
Cytowane przez
Pokaż
ISSN
0137-5520
Język
eng
URI / DOI
http://dx.doi.org/10.5604/01.3001.0055.1459
Udostępnij na Facebooku Udostępnij na Twitterze Udostępnij na Google+ Udostępnij na Pinterest Udostępnij na LinkedIn Wyślij znajomemu