Financial Research Journal

Financial Research Journal

Modeling and Predicting Initial Public Offering Returns Using Gradient Boosting Machine Learning Algorithms

Document Type : Research Paper

Authors
Fatemeh Malmir 1
Farshid Kheirollahi 2
Hossein Yarahmadi 3
Farid Sefaty 4
1 Ph.D. Candidate, Department of Accounting, Bo.C., Islamic Azad University, Borujerd, Iran.
2 Assistant Prof., Department of Accounting, Faculty Economic and Accounting, Razi University, Kermanshah, Iran.
3 Assistant Prof., Department of Computer Engineering, Bo.C., Islamic Azad University, Borujerd, Iran,
4 Assistant Prof., Department of Accounting, Bo.C., Islamic Azad University, Borujerd, Iran.
10.22059/frj.2025.400625.1007779
Abstract
Objective
This research aims to develop a novel model based on the Gradient Boosting algorithm and Transformer architecture for accurately predicting corporate valuation ratios at the time of an Initial Public Offering (IPO) in the Iranian market. Contrary to traditional approaches focusing on first-day returns, this study evaluates the relative pricing of companies through three key ratios: Price-to-Book Value (P/B), Enterprise Value-to-Total Assets (EV/TA), and Enterprise Value-to-Sales (EV/S). Given the complexities of the Iranian market, including severe economic volatility, chronic inflation, economic sanctions, and regulatory restrictions, this research provides an efficient tool for investors, underwriters, and regulatory bodies to make more informed decisions.

Methods
This quantitative applied study analyzes data from 163 companies, including 42 firms listed on the Tehran Stock Exchange and 121 firms traded on the over-the-counter market (Farabourse), covering the period from 2013 to 2023 (1392–1402 in the Iranian calendar). This period encompasses diverse economic conditions, including severe sanctions, currency fluctuations, recession, and economic booms. Independent variables included firm-specific financial features (size, debt ratio, profitability, return on assets, profit margin, cash flow ratio, financial leverage, and weighted average cost of capital) and macroeconomic variables (inflation rate, main stock market index, sanctions index, exchange rate, and interest rate). The proposed architecture is a hybrid of Gradient Boosting Decision Trees, Long Short-Term Memory (LSTM) networks, and self-attention mechanisms, optimized through an Automated Machine Learning (AutoML) architecture search. The optimal model configuration consisted of a learning rate of 0.001, 150 decision trees, four time steps, and three self-attention layers. The proposed model was compared with traditional methods (i.e., linear regression) and advanced approaches, including standard gradient boosting algorithms, random forests, and recurrent neural networks. Model performance was evaluated using ten-fold cross-validation and bootstrapping.

Results
The results demonstrated the decisive superiority of the proposed model in predicting all three valuation ratios. For the Price-to-Book Value ratio, the developed model achieved an R2 of 0.853 and a Root Mean Square Error (RMSE) of 0.497, representing a 60% improvement in prediction accuracy compared to Linear Regression (R2 of 0.534). In predicting the Enterprise Value-to-Total Assets (EV/TA) ratio, the model achieved an R² of 0.865 and reduced the Mean Squared Error (MSE) by 69%, from 0.152 to 0.047. For the Enterprise Value-to-Sales ratio, an R2 of 0.846 was achieved, showing a 67% improvement in accuracy over traditional methods. Other advanced models also performed acceptably but did not reach the level of the proposed model. Cross-validation tests confirmed the model's high stability with a very low standard deviation (around 0.01), indicating its generalizability and reliability under various conditions. Variable importance analysis revealed that the inflation rate acts as the second most important factor across all models, with an average importance of 0.19, indicating the profound impact of macroeconomic conditions on corporate valuation in the Iranian market. Return on Assets (ROA) was identified as the most influential financial performance indicator for the P/B ratio (0.210), Profit Margin for the EV/S ratio (0.225), and Cash Flow-to-Assets Ratio for the EV/TA ratio (0.2).

Conclusion
The findings emphasize the importance of employing novel machine learning techniques in predicting IPO valuation ratios. The developed model, by reducing prediction error by 60% to 69%, provides an advanced tool for underwriters, investors, and fund managers to mitigate the risk of undervaluation or overvaluation. The identification of the pivotal role of the inflation rate highlights the high sensitivity of valuations to macroeconomic conditions in the Iranian market. This research contributes to three key areas: introducing a novel hybrid architecture, providing a comprehensive validation framework, and identifying the differential importance of variables for various valuation ratios under unstable economic conditions.
Keywords
Prediction
Initial Public Offering (IPO)
Gradient boosting algorithm
Machine learning
Iranian capital market
Subjects
 
References
Abbas Hasan, S., Piri, P. & Chalaki, P. (2025). Designing an optimal decision-making model for investors: Integrating artificial intelligence and financial reporting transparency. Journal of Asset Management and Financing, 12(4), 1-22. https://doi.org/10.22108/amf.2025.143308.1934 (in Persian)
Abbasi, E. & Marezloo, V. (2011). Survey on the Influence of Free Float Stock on Liquidity Indices in Tehran Stock Exchange. Financial Accounting Research, 3(3), 147-161.
(in Persian)
Abbasian, E., Shahraki, K., Fallahpour, S. & Namaki, A. (2023). A novel approach to predicting financial distress by using financial network-based information and the integrated method of gradient boosting decision tree. Journal of Asset Management and Financing, 11(3), 113-140. https://doi.org/10.22108/amf.2023.138909.1818 (in Persian)
Abedian, N. & Mousavi, S. R. (2024). Banking under sanctions. Scientific Journal of New Research Approaches in Management and Accounting, 8(30), 443–459. (in Persian)
Afsharirad, E., Alavi, S. E. & Sinaei, H. (2018). Developing an Intelligent Model to Predict Stock Trend Using the Technical Analysis. Financial Research Journal, 20(2), 249–264. https://doi.org/10.22059/frj.2018.233763.1006452 (in Persian)
Aghaei, M. (2025). An empirical analysis of herding behavior in the stock market: Evidence from various economic and social conditions in Iran. Journal of Asset Management and Financing, 13(3), 29-56. https://doi.org/10.22108/amf.2025.142503.1913 (in Persian)
Alahmadi, M. (2025). A deep learning-based ensemble framework to predict IPOs performance for sustainable economic development. Sustainability, 17(3), 827. https://doi.org/10.3390/su17030827
Aldana, C. M. & Trigos, F. (2025). A transdisciplinary engineering framework for analysing initial public offerings' financial behaviour. International Journal of Agile Systems and Management, 18(1), 112-132.
Baba, B. & Sevil, G. (2020). Predicting IPO initial returns using random forest. Borsa Istanbul Review, 20(1), 13–23. https://doi.org/10.1016/j.bir.2019.08.001
Baker, M. & Wurgler, J. (2006). Investor sentiment and the cross-section of stock returns. The Journal of Finance, 61(4), 1645-1680. https://doi.org/10.1111/j.1540-6261.2006.00885.x
Bateni, L., Poorzamani, Z. & Rahnama Rood Poshti, F. (2013). Investigation of impact of after-market liquidity on IPO price in Tehran Stock Exchange. Journal of Asset Management and Financing, 1(1), 63-74. (in Persian)
Benveniste, L. M. & Spindt, P. A. (1989). How investment bankers determine the offer price and allocation of new issues. Journal of Financial Economics, 24(2), 343-361. https://doi.org/10.1016/0304-405X(89)90051-2
Chen, T. & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785-794). https://doi.org/10.1145/2939672.2939785
Chen, Y., Goyal, A., Veeraraghavan, M. & Zolotoy, L. (2020). Terrorist attacks, investor sentiment, and the pricing of initial public offerings. Journal of Corporate Finance, 65, 101780. https://doi.org/10.1016/j.jcorpfin.2020.101780
Daryaei, A. A., Azizi, P. & Fattahi, Y. (2022). Conservatism and initial public offerings (IPOs) underpricing: An audit quality perspective. Iranian Journal of Finance, 6(4), 125-159. https://doi.org/10.30699/ijf.2022.284931.1230
Derrien, F. & Womack, K. (2003). Auctions vs. book-building and the control of underpricing in hot IPO markets. Review of Financial Studies, 16(1), 31-61. https://doi.org/10.1093/rfs/16.1.31
Drooduin, T. (2023). IPO Underpricing and overpricing and long-term firm performance in the Netherlands, United Kingdom, France, Sweden, and Italy: learning from three Dutch IPOs. Central European Review of Economics and Management (CEREM), 7(4), 109-158.
Duan, Y., Schulman, J., Chen, X., Bartlett, P. L., Stiennon, N. & Amodei, D. (2016). Fast reinforcement learning via slow reinforcement learning. arXiv. https://doi.org/10.48550/arXiv.1611.02779
Engelen, P.-J. & van Essen, M. (2010). Underpricing of IPOs: Firm-, issue- and country-specific characteristics. Journal of Banking & Finance, 34(8), 1958-1969. https://doi.org/10.1016/j.jbankfin.2010.01.002
Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. The Journal of Finance, 25(2), 383-417. https://doi.org/10.2307/2325486
Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189-1232. https://doi.org/10.1214/aos/1013203451
Füllbrunn, S., Neugebauer, T. & Nicklisch, A. (2014). Underpricing of initial public offerings in experimental asset markets. NiCE Working Paper 14-107. Radboud University Nijmegen, The Netherlands. https://doi.org/10.1007/s10683-019-09638-7
Gan, L., Wang, H. & Yang, Z. (2020). Machine learning solutions to challenges in finance: An application to the pricing of financial products. Technological Forecasting and Social Change, 153, 119928. https://doi.org/10.1016/j.techfore.2020.119928
Geertsema, P. & Lu, H. (2022). Relative valuation with machine learning. Journal of Accounting Research, 61(1), 329-376. https://doi.org/10.1111/1475-679X.12464
Ghafari, A., Arabzadeh, M., Safari Gerayli, M., Jabbary, H. & Rezaei Pitenoei, Y. (2023). Corporate integrity and information asymmetry: Evidence from Iran. Iranian Journal of Finance, 7(4), 90-119. https://doi.org/10.61186/ijf.2023.369566.1381
Ghallabi, F., Souissi, B., Du, A. M. & Ali, S. (2025). ESG stock markets and clean energy prices prediction: Insights from advanced machine learning. International Review of Financial Analysis, 97(1), 103889. https://doi.org/10.1016/j.irfa.2024.103889
Ghasseminejad, S. & Jahan-Parvar, M. R. (2021). The impact of financial sanctions: The case of Iran. Journal of Policy Modeling, 43(1), Article 10.1016/j.jpolmod.2021.03.001. https://doi.org/10.1016/j.jpolmod.2021.03.001
Gupta, V., & Kumar, E. (2023). H3O-LGBM: hybrid Harris hawk optimization based light gradient boosting machine model for real-time trading. Artificial Intelligence Review, 56(8), 8697-8720.
Heidari Haratemeh, M. & Ebrahimi, B. (2024). Investigating the impact of IPO on the financial performance of companies. Modern Research in Performance Evaluation, 2(4), 240-252. https://doi.org/10.22105/mrpe.2024.451424.1096 (in Persian)
Heidari, M. & Amiri, H. (2022). Inspecting the Predictive Power of Artificial Intelligence Models in Predicting the Stock Price Trend in Tehran Stock Exchange. Financial Research Journal, 24(4), 602–623. https://doi.org/10.22059/frj.2022.320064.1007149
(in Persian)
Heybati, F. & Moradi, Z. (2010). Initial public offering pricing in Tehran Stock Exchange. Financial Knowledge of Securities Analysis, 3(6), 19-48. https://sid.ir/paper/200375/fa
(in Persian)
Heydarian, S., Pahlavani, M. & Mirjalili, S. H. (2025). Financial sanction, exchange rate volatility and macroeconomic variables (Case of Iran). Iranian Journal of Finance, 9(2), 70-106. https://doi.org/10.61186/ijf.2025.462663.1476
Hosseini, S. H., Ebrahimi Sarv Oliya, M. H., Amiri, M. & Peymanifurushani, M. (2023). Liquidity risk management framework of mutual funds. Journal of Asset Management and Financing, 11(1), 53-76. https://doi.org/10.22108/amf.2023.133686.1744
(in Persian)
Huma, Z. & Nishat, A. (2024). Optimizing stock price prediction with LightGBM and engineered features. Pioneer Research Journal of Computing Science, 1(1), 59–67. Retrieved from https://prjcs.com/index.php/prjcs/article/view/17
Ibbotson, R. G. (1975). Price performance of common stock new issues. Journal of Financial Economics, 2(3), 235-272. https://doi.org/10.1016/0304-405X(75)90015-X
Ibbotson, R. G., Sindelar, J. L. & Ritter, J. (1994). The market's problems with the pricing of initial public offerings. Journal of Applied Corporate Finance, 7(1), 66-74. https://doi.org/10.1111/j.1745-6622.1994.tb00395.x
Jamaani, F. & Alidarous, M. (2019). Review of theoretical explanations of IPO underpricing. Journal of Accounting Business and Finance Research, 6(1), 1-18. https://doi.org/10.20448/2002.61.1.18
Kamyabi, Y. & Borbori, F. (2016). Moral hazard and asymmetric information in IPO underpricing. Journal of Accounting and Social Interests, 6(1), 21-42. https://doi.org/10.22051/ijar.2016.236 (in Persian)
Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., Ye, Q. & Liu, T.-Y. (2017). LightGBM: A highly efficient gradient boosting decision tree. In Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS '17) (pp. 3149-3157). https://doi.org/10.1109/NIPS.2017.24436
Khadivi, H., Bahri Sales, J., Jabbarzadeh Kangarluyi, S. & Zavarirezaei, A. (2022). Investigating the impact of the devaluation of national currency and macroeconomic indicators considering the political effects of sanctions on stock prices. International Journal of Nonlinear Analysis and Applications, 13(2), 1089-1103. https://doi.org/10.22075/ijnaa.2021.23849.2624
Khan, A. A., Chaudhari, O. & Chandra, R. (2024). A review of ensemble learning and data augmentation models for class imbalanced problems: Combination, implementation and evaluation. Expert Systems with Applications, 244, 122778. https://doi.org/10.1016/j.eswa.2023.122778
Khatami, S.M.R., Zomorodian, Gh.R., Fallah Shams Layalestani, M.F. & Minouei, M. (2022). Examining the Interdependence Structure of Iran's Stock Market and MENA Countries. Financial Economics, 16(61), 273-310. 10.30495/fed.2023.698852
Lashgarara, S., Khodadadi, V., Mazaheri, E. & Ayati Mehr, M. (2023). Assessing the risk of falling stock prices and its alignment with price bubbles based on the rational stock pricing structure. Financial Accounting Research, 15(3), 1-28. https://doi.org/10.22108/far.2023.138880.1992 (in Persian)
Lee, S. H., Bach, S. & Baik, Y.-S. (2011). The impact of IPOs on the values of directly competing incumbents. Strategic Entrepreneurship Journal, 5(2), 158-177. https://doi.org/10.1002/sej.112
Li, J. & Li, Z. (2025). Mechanisms of corporate digital transformation on asymmetric capital structure adjustment—the mediating role of information asymmetry and financial stability. Heliyon, 11(3), e41745. https://doi.org/10.1016/j.heliyon.2025.e41745
Li, S. (2023). Estimating stock market prices with histogram-based gradient boosting regressor: A case study on Alphabet Inc. International Journal of Advanced Computer Science and Applications, 15(5), 532-544. https://doi.org/10.14569/IJACSA.2024.0150553
Lin, C. Y. & Marques, J. A. (2024). Stock market prediction using artificial intelligence: A systematic review of systematic reviews. Social Sciences & Humanities Open, 9(1), 100864. https://doi.org/10.1016/j.ssaho.2024.100864
Liu, C., Yan, J., Guo, F. & Guo, M. (2022). Forecasting the market with machine learning algorithms: An application of NMC-BERT-LSTM-DQN-X algorithm in quantitative trading. ACM Transactions on Knowledge Discovery from Data, 16(4), 1–22. https://doi.org/10.1145/3488378
López-Cabarcos, M. Á., Pérez-Pico, A. M., Vázquez Rodríguez, P. & López-Pérez, M. L. (2019). Investor sentiment in the theoretical field of behavioural finance. Economic Research-Ekonomska Istraživanja, 33(3), 1-19. https://doi.org/10.1080/1331677X.2018.1559748
Malmir, F., Kheirollahi, F., Yarahmadi, H. & Sefaty, F. (2025). Application of gradient boosting algorithm in predicting relative pricing of initial public offerings: A case study of the Iranian stock exchange. Business, Marketing, and Finance Open, 2(5), 1-21. https://www.bmfopen.com/index.php/bmfopen/article/view/236
Manosuri, A., Momeni, M. & Kazemi Miyangaskary, M. (2026). Integrating Stock Levels into Demand Forecasting and Discount Optimization for Retail. Industrial Management Journal, 18(2), 183-207.
Naderi, Sh. & Espoukeh, J. (2016). Identify factors affecting on under pricing of initial public offering (IPO) shares of listed companies Tehran Stock Exchange. Financial Knowledge of Securities Analysis, 31, 97-109. https://sid.ir/paper/200252/fa (in Persian)
Najafi, S., Bahrami, R. & Hosseini, N. (2023). Sentiment analysis and its impact on stock market volatility: Leveraging natural language processing techniques. Accounting, Finance and Computational Intelligence, 1(1), 13-27. https://jafci.com/index.php/jafci/article/view/3 (in Persian)
Nakagawa, K. & Yoshida, K. (2022). Time-series gradient boosting tree for stock price prediction. International Journal of Data Mining, Modelling and Management, 14(2), 110-125. https://doi.org/10.1504/IJDMMM.2022.123357
Nasiri Aghdam, A., Jafari Shahrestani, A., Gholami, E. & Pirooz Rahi, Z. (2024). Lessons from Privatization of State-owned Enterprises in Iran A Case Study of Raja Passenger Train Company, Iran Airtour Airlines, Haft Tappeh Sugarcane Agro-industrial Company and Al Mahdi Aluminum Complex. Majlis and Rahbord, 31(118), 5–45. https://doi.org/10.22034/mr.2023.5407.5162 (in Persian)
Nikpey Pesyan, V., Reza Zadeh, A., Ahmadi Nezhad, H. & Ahmad Vand, S. (2023). Investigating the causal relationship between stocks’ initial public offerings and macroeconomic variables. Journal of Asset Management and Financing, 11(2), 35-52. https://doi.org/10.22108/amf.2023.136359.1779 (in Persian)
Quintana, D., Sáez, Y. & Isasi, P. (2017). Random forest prediction of IPO underpricing. Applied Sciences, 7(6), 636. https://doi.org/10.3390/app7060636
Rezaeyan, S., Taleghani, M. & Sherej Sharifi, A. (2024). Development of a comprehensive model to predict stock prices in the stock market with an interpretive structural modeling approach. Journal of Asset Management and Financing, 12(2), 39-58. https://doi.org/10.22108/amf.2024.138983.1821 (in Persian)
Ross, S. A. (1977). The determination of financial structure: The incentive-signalling approach. The Bell Journal of Economics, 8(1), 23-40. https://doi.org/10.2307/3003485
Roy, S. S., Chopra, R., Lee, K. C., Spampinato, C. & Mohammadi-Ivatlood, B. (2020). Random forest, gradient boosted machines and deep neural network for stock price forecasting: A comparative analysis on South Korean companies. International Journal of Ad Hoc and Ubiquitous Computing, 33(1), 62-71. https://doi.org/10.1504/IJAHUC.2020.104715
Saeidi Aghdam, M., Sadeghi, A., Bahiraie, A. & Haji Asghari, S. Y. (2023). Provide a stock price forecasting model using deep learning algorithms and its use in the pricing of Islamic bank stocks. Islamic Economics & Banking, 11(41), 5. http://mieaoi.ir/article-1-964-fa.html (in Persian)
Schmitt, M. (2022). Deep learning vs. gradient boosting: Benchmarking state-of-the-art machine learning algorithms for credit scoring. arXiv. https://doi.org/10.48550/arXiv.2205.10535
Shojaei, M., Abdolbaghi Ataabadi, A. & Shirvani, A. (2021). Investigating the effect of non – systematic fluctuations on mispricing: Evidence of Companies Listed in Tehran Stock Exchange. Journal of Financial Accounting Research, 12(4), 79-100. (in Persian)
Subasi, A. (2020). Machine learning techniques. In Practical Machine Learning for Data Analysis Using Python (pp. 91-202). https://doi.org/10.1016/B978-0-12-821379-7.00003-5
Taheri Haftasiabi, R. & Naderi, A. (2025). Earnings per share prediction and actual earnings management using optimal valuation of operating assets. Public Sector Accounting and Budgeting, 5(4), 138-164. https://doi.org/10.22034/psab.2025.213907 (in Persian)
Vaghfi, S. H., Sedighe, G., Parandin, K. & Hosseini Aghdaei, S. (2025). The role of ownership structure of stock in moderating the relationship between stock price concurrency and mispricing. Journal of Management Accounting and Auditing Knowledge, 14(55), 177-192. https://www.jmaak.ir/article_23622.html (in Persian)
Vaidynathan, D., Kayal, P. & Maiti, M. (2025). A feature engineering based model architecture for modeling initial public offerings. Applied Soft Computing, 174, 113035.
Vasić, A.S. (2020). The Importance of Initial Public Offering for Capital Market Development in Developing Countries. Economic Themes 58(1), 97-115. DOI:10.2478/ethemes-2020-0006
Zareei, A., Falahi, M. A. & Maleksadati, S. S. (2024). The impact of international sanctions on Iran's economy with an emphasis on the role of the National Development Fund: DSGE model approach. The Journal of Economic Policy, 16(31), 35-80. https://doi.org/10.22034/epj.2024.20548.2483
Zhang, J., Cai, K. & Wen, J. (2024). A survey of deep learning applications in cryptocurrency. iScience, 27(1), 108509. https://doi.org/10.1016/j.isci.2023.108509
Financial Research Journal
Volume 28, Issue 3
2026
Pages 885-932