Article Sidebar
Main Article Content
This study investigates the application of Large Language Models (LLMs) for forecasting Earnings Per Share (EPS) on the Warsaw Stock Exchange, comparing Google's Gemini model against the seasonal random walk (SRW) approach. Analyzing quarterly EPS data from 267 Polish companies (2010-2019), the mean arctangent absolute percentage error (MAAPE) is employed to address limitations of traditional error metrics. Results demonstrate that despite Gemini's sophisticated capabilities, the simpler SRW model consistently produces lower error rates when measured by MAAPE, although Gemini outperforms on RMSE and MAE metrics. The divergence highlights how model selection should be guided by specific error tolerance requirements. Additionally, we explore Gemini's chain-of-thought reasoning and certainty scores to assess model confidence. These findings contribute to the understanding of EPS prediction in emerging markets with limited analyst coverage and suggest that complex models may not provide significant advantages in markets characterized by relatively unsophisticated EPS dynamics.
Article Details
Abarbanell J., Bushee B. (1997) Fundamental Analysis, Future EPS, and Stock Prices. Journal of Accounting Research, 35(1), 1-24. https://doi.org/10.2307/2491464 (Crossref)
Beating the Machine … 23
Abdelsamie M., Wang H. (2024) Comparative Analysis of LLM-based Market Prediction and Human Expertise with Sentiment Analysis and Machine Learning Integration. 2024 7th International Conference on Data Science and Information Technology (DSIT), 1-6. https://doi.org/10.1109/dsit61374.2024.10881868 (Crossref)
Abe Y., Matsuo S., Kondo R., Hisano R. (2024) Leveraging Large Language Models for Institutional Portfolio Management: Persona-Based Ensembles. 2024 IEEE International Conference on Big Data (BigData), 4799-4808. https://doi.org/10.1109/bigdata62323.2024.10825362 (Crossref)
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. https://doi.org/10.1007/s10614-014-9455-6 (Crossref)
Atiya A., Shaheen S., Talaat N. (1997) An Efficient Stock Market Forecasting Model using Neural Networks. IEEE International Conference on Neural Networks – Conference Proceedings. http://dx.doi.org/10.1109/ICNN.1997.614231 (Crossref)
Ball R., Ghysels E. (2017) Automated Earnings Forecasts: Beat Analysts or Combine and Conquer? Management Science, 64(10), 4936–4952. https://doi.org/10.1287/mnsc.2017.2864 (Crossref)
Ball R., Watts R. (1972) Some Time Series Properties of Accounting Income. The Journal of Finance, 27(3), 663-681. http://dx.doi.org/10.1111/j.1540-6261.1972.tb00991.x (Crossref)
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. (Crossref)
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. http://dx.doi.org/10.1007/s11142-012-9185-8 (Crossref)
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. http://dx.doi.org/10.1108/eb013581 (Crossref)
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. http://dx.doi.org/10.1111/j.1540-6261.1976.tb03218.x (Crossref)
Brown L. D., Griffin P. A., Hagerman R. L., Zmijewski 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. http://dx.doi.org/10.1016/0165-4101(87)90017-6 (Crossref)
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. http://dx.doi.org/10.2307/2490312 (Crossref)
Cao Q., Gan Q. (2009) Forecasting EPS of Chinese Listed Companies using a Neural Network with Genetic Algorithm. 15th Americas Conference on Information Systems 2009, AMCIS 2009, 2791-2981.
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. https://doi.org/10.1016/j.dss.2008.12.011 (Crossref)
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. https://doi.org/10.1111/j.00117315.2004.02674.x (Crossref)
Cao R., Wang Q. (2024) An Evaluation of Standard Statistical Models and LLMs on Time Series Forecasting. 2024 IEEE International Conference on Future Machine Learning and Data Science (FMLDS), 533-538. https://doi.org/10.1109/fmlds63805.2024.00098 (Crossref)
Cao Y., Chen Z., Pei Q., Lee N., Subbalakshmi K. P., Ndiaye P. M. (2024) ECC Analyzer: Extracting Trading Signal from Earnings Conference Calls using Large Language Model for Stock Volatility Prediction. Proceedings of the 5th ACM International Conference on AI in Finance, 257-265. https://doi.org/10.1145/3677052.3698689 (Crossref)
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. https://doi.org/10.3390/sym12101620 (Crossref)
Chong C. Y., Kao H.-Y. (2025) Rationale-Driven Predictions for Stock Movements: A Multi-model Integration and Stack Generalization Approach. Technologies and Applications of Artificial Intelligence, 124-138. https://doi.org/10.1007/978-981-96-4589-3_9 (Crossref)
Conroy R., Harris R. (1987) Consensus Forecasts of Corporate Earnings: Analysts’ Forecasts and Time Series Methods. Management Science, 33(6), 725-738. http://dx.doi.org/10.1287/mnsc.33.6.725 (Crossref)
Elend L., Kramer O., Lopatta K., Tideman S. (2020) Earnings Prediction with Deep Learning. German Conference on Artificial Intelligence (Künstliche Intelligenz) KI 2020: Advances in Artificial Intelligence, 267-274. http://dx.doi.org/10.1007/978-3-030-58285-2_22 (Crossref)
Elton E. J., Gruber M. J. (1972) Earnings Estimates and the Accuracy of Expectational Data. Management Science, 18(8), B409-B424. http://dx.doi.org/10.1287/mnsc.18.8.B409 (Crossref)
Foster G. (1977) Quarterly Accounting Data: Time-Series Properties and Predictive-Ability Results. The Accounting Review, 52(1), 1-21. (Crossref)
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. https://doi.org/10.1590/1678-6971/eramf210164 (Crossref)
Gomez A. N., Kaiser L., Jones L., Parmar N., Polosukhin I., Vaswani A., Shazeer N., Uszkoreit J. (2017) Attention Is All You Need. arXiv preprint arXiv:1706.03762.
Google DeepMind. (2023) Gemini: A Family of Highly Capable Multimodal Models. arXiv. https://arxiv.org/abs/2312.1180
Griffin P. (1977) The Time-Series Behavior of Quarterly Earnings: Preliminary Evidence. Journal of Accounting Research, 15(1), 71-83. http://dx.doi.org/10.2307/2490556 (Crossref)
Gupta R., Khirbat G., Singh S. (2013) Optimal Neural Network Architecture for Stock Market Forecasting. Proceedings – 2013 International Conference on Communication Systems and Network Technologies, CSNT 2013, 557-561. https://doi.org/10.1109/csnt.2013.120 (Crossref)
Harris R. D. F., Wang P. (2019) Model-Based Earnings Forecasts vs. Financial Analysts’ Earnings Forecasts. British Accounting Review, 51(4), 424-437. https://doi.org/10.1016/j.bar.2018.10.002 (Crossref)
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. https://doi.org/10.1016/j.jacceco.2011.12.001 (Crossref)
Hou G., Lian Q. (2024) Benchmarking of Commercial Large Language Models: ChatGPT, Mistral, and Llama. ResearchSquare. https://doi.org/10.21203/rs.3.rs-4376810/v1 (Crossref)
Jarrett J. E. (2008) Evaluating Methods for Forecasting Earnings Per Share. Managerial Finance, 16, 30-35. http://dx.doi.org/10.1108/eb013647 (Crossref)
Johnson T. E., Schmitt T. G. (1974) Effectiveness of Earnings Per Share Forecasts. Financial Management, 3(2), 64-72. http://dx.doi.org/10.2307/3665292 (Crossref)
Kim S., Kim H. (2016) A New Metric of Absolute Percentage Error for Intermittent Demand Forecasts. International Journal of Forecasting, 32(3), 669-679. http://dx.doi.org/10.1016/j.ijforecast.2015.12.003 (Crossref)
Kong Y., Nie Y., Dong X., Mulvey J. M., Poor H. V., Wen Q., Zohren S. (2024) Large Language Models for Financial and Investment Management: Models, Opportunities, and Challenges. The Journal of Portfolio Management, 51(2), 211-231. https://doi.org/10.3905/jpm.2024.1.646 (Crossref)
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. http://dx.doi.org/10.7172/2353-6845.jbfe.2023.1.2 (Crossref)
Kuryłek W. (2023b) Can Exponential Smoothing Do Better than Seasonal Random Walk for Earnings Per Share Forecasting in Poland? Bank Credit, 54(6), 651-672. (Crossref)
Kuryłek W. (2024a) 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. http://dx.doi.org/10.3934/DSFE.2024008 (Crossref)
Kuryłek W. (2024b) Artificial Neural Networks and Gradient-Boosting Decision Trees in Time Series Forecasting of Earnings Per Share in Poland. Eastern European Economics, 1-22. https://doi.org/10.1080/00128775.2024.2429137 (Crossref)
Kuryłek W. (2024c) If Multilayer Perceptron Network May Help in Multivariate EPS Forecasting. Evidence from Poland. Quantitative Methods in Economics, 25(3), 107-123. https://doi.org/10.22630/mibe.2024.25.3.10 (Crossref)
Kuryłek W. (2025) Are Natural Language Processing Methods Applicable to EPS Forecasting in Poland? Data Science in Finance and Economics, 5(1), 35-52. https://doi.org/10.3934/dsfe.2025003 (Crossref)
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 (pp. 77-101) Bingley, UK: Emerald. http://dx.doi.org/10.1108/S1477-4070(2011)0000008009 (Crossref)
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. http://dx.doi.org/10.1080/09603100600592752 (Crossref)
Lev B., Thiagarajan S. (1993) Fundamental Information Analysis. Journal of Accounting Research, 31(2), 190–215. http://doi.org/10.2307/2491270 (Crossref)
Lev B., Li S., Sougiannis T. (2010) The Usefulness of Accounting Estimates for Predicting Cash Flows and Earnings. Review of Accounting Studies, 15(4), 779-807. https://doi.org/10.1007/s11142-009-9107-6 (Crossref)
Li K. K. (2011) How Well Do Investors Understand Loss Persistence? Review of Accounting Studies, 16(3), 630-667. https://doi.org/10.1007/s11142-011-9157-4 (Crossref)
Wojciech Kuryłek
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. https://doi.org/10.1007/s11142-014-9282-y (Crossref)
Lorek K. S. (1979) Predicting Annual Net Earnings with Quarterly Earnings Time-Series Models. Journal of Accounting Research, 17(1), 190-204. http://dx.doi.org/10.2307/2490313 (Crossref)
Lorek K. S., Willinger G. L. (1996) A Multivariate Time-Series Model for Cash-Flow Data. Accounting Review, 71, 81-101. (Crossref)
Ohlson J. A. (1995) Earnings, Book Values, and Dividends in Equity Valuation. Contemporary Accounting Research, 11(2), 661-687. https://doi.org/10.1092/7tpj-rxqn-tqc7-ffae (Crossref)
Ohlson J. A. (2001) Earnings, Book Values, and Dividends in Equity Valuation: An Empirical Perspective. Contemporary Accounting Research, 18(1), 107-120. https://doi.org/10.1092/7tpj-rxqn-tqc7-ffae (Crossref)
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. http://dx.doi.org/10.1016/j.adiac.2020.100497 (Crossref)
Pope P. F., Wang P. (2005) Earnings Components, Accounting Bias and Equity Valuation. Review of Accounting Studies, 10(4), 387-407. https://doi.org/10.1007/s11142-005-4207-4 (Crossref)
Pope P., Wang P. (2014) On the Relevance of Earnings Components: Valuation and Forecasting Links. Review of Quantitative Finance and Accounting, 42, 399-413. https://doi.org/10.1007/s11156-013-0347-y (Crossref)
Ruland W. (1980) On the Choice of Simple Extrapolative Model Forecasts of Annual Earnings. Financial Management, 9(2), 30-37. http://dx.doi.org/10.2307/3665165 (Crossref)
Sarker I. H. (2024) LLM Potentiality and Awareness: A Position Paper from the Perspective of Trustworthy and Responsible AI Modeling. https://doi.org/10.36227/techrxiv.170905626.67078570/v1 (Crossref)
Watts R. L. (1975) The Time Series Behavior of Quarterly Earnings. Working paper, Department of Commerce, University of New Castle.
Wilcoxon F. (1945) Individual Comparisons by Ranking Methods. Biometrics, 1, 80-83. http://dx.doi.org/10.2307/3001968 (Crossref)
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) https://doi.org/10.1109/icetci55101.2022.9832404 (Crossref)
Downloads
- Wojciech Kuryłek, If Multilayer Perceptron Network May Help in Multivariate EPS Forecasting. Evidence from Poland. , Metody Ilościowe w Badaniach Ekonomicznych: Tom 25 Nr 3 (2024)
Utwór dostępny jest na licencji Creative Commons Uznanie autorstwa – Użycie niekomercyjne 4.0 Międzynarodowe.
Publikowane artykuły dostępne są na warunkach Open Access na zasadach licencji Creative Commons CC BY-NC – do celów niekomercyjnych udostępnione materiały mogą być kopiowane, drukowane i rozpowszechniane. Autorzy ponoszą opłatę za opublikowanie artykułu.