Research on Multimodal Prediction Model of Sports Event Ticket Revenue Based on Transformer

Qian Zhang

doi:10.71451/ISTAER2618

Authors

Qian Zhang College of Physical Education and Health Science, Yibin University, Yibin, Sichuan, China Author https://orcid.org/0009-0006-6264-5818

DOI:

https://doi.org/10.71451/ISTAER2618

Keywords:

Sports events; Ticket revenue forecasting; Multimodal learning; Transformer; Time series prediction

Abstract

To address the problem that sports event ticket revenue is affected by the coupling of multiple factors and exhibits significant dynamic changes, this paper proposes a multimodal prediction model based on Transformer. This method integrates historical ticketing data, event information, user behavior, and public opinion data, constructs a cross‑modal dynamic alignment Transformer architecture (CMDA‑Transformer), and introduces a multi‑scale time series modeling mechanism and a demand sensitivity enhancement module to improve the model's ability to capture complex temporal patterns and multi‑source information. Experiments were conducted on about 24,000 real event records. The results show that compared with traditional ARIMA, XGBoost, and deep learning models (LSTM, GRU, and standard Transformer), the RMSE of this method is 18.72, which is about 5.7% lower than that of the baseline Transformer, the MAPE is about 8.3% lower, and the coefficient of determination increases to 0.912. At the same time, it still maintains stable performance under different types of events and noise interference scenarios, which verifies the generalization ability and robustness of the model. The results show that this method can effectively improve the accuracy of ticket revenue prediction, and provide reliable support for dynamic pricing and ticket optimization.

References

[1] Bradbury, J. C., Coates, D., & Humphreys, B. R. (2023). The impact of professional sports franchises and venues on local economies: A comprehensive survey. Journal of Economic Surveys, 37(4), 1389-1431. DOI: https://doi.org/10.2139/ssrn.4022547

[2] Geng, X., Hall, N. G., Mallipeddi, R. R., & Tan, Y. EXPRESS: The Business of Sports: an Operations Perspective. Production and Operations Management, 10591478251406726. DOI: https://doi.org/10.1177/10591478251406726

[3] Paul, A. K. (2023). Future of sports operations and sports event management in uncertain environment: a critical review. Sports Management in an Uncertain Environment, 189-218. DOI: https://doi.org/10.1007/978-981-19-7010-8_9

[4] McDonald, H., Dunn, S., Schreyer, D., & Sharp, B. (2024). Understanding consumer behaviour in evolving subscription markets–lessons from sports season tickets research. Journal of Service Management, 35(1), 89-107. DOI: https://doi.org/10.1108/josm-03-2022-0116

[5] Toner, J., Wardman, M., Shires, J., Teklu, F., & Hatfield, A. (2020). Enhancing rail direct demand models with competition between ticket types using contributions from economic theory and market research. Transportation Research Part A: Policy and Practice, 138, 127-144. DOI: https://doi.org/10.1016/j.tra.2020.05.017

[6] Wang, X., Li, A., & Han, G. (2023). A deep-learning-based fault diagnosis method of industrial bearings using multi-source information. Applied Sciences, 13(2), 933. DOI: https://doi.org/10.3390/app13020933

[7] Guo, D., Yang, X., Peng, P., Zhu, L., & He, H. (2025). The intelligent fault identification method based on multi-source information fusion and deep learning. Scientific Reports, 15(1), 6643. DOI: https://doi.org/10.1038/s41598-025-90823-5

[8] Algiriyage, N., Prasanna, R., Stock, K., Doyle, E. E., & Johnston, D. (2022). Multi-source multimodal data and deep learning for disaster response: a systematic review. SN Computer Science, 3(1), 92. DOI: https://doi.org/10.1007/s42979-021-00971-4

[9] Wang, Y., Zhang, Z., Feng, L., Du, Q., & Runge, T. (2020). Combining multi-source data and machine learning approaches to predict winter wheat yield in the conterminous United States. Remote Sensing, 12(8), 1232. DOI: https://doi.org/10.3390/rs12081232

[10] Yang, D., Li, M., Qu, L., Yang, K., Zhai, P., Wang, S., & Zhang, L. (2024). Asynchronous multimodal video sequence fusion via learning modality-exclusive and-agnostic representations. IEEE Transactions on Circuits and Systems for Video Technology, 34(12), 12360-12375. DOI: https://doi.org/10.1109/TCSVT.2024.3435561

[11] Adekunle, B. I., Chukwuma-Eke, E. C., Balogun, E. D., & Ogunsola, K. O. (2021). Predictive analytics for demand forecasting: Enhancing business resource allocation through time series models. Journal of Frontiers in Multidisciplinary Research, 2(01), 32-42. DOI: https://doi.org/10.54660/.ijfmr.2021.2.1.32-42

[12] Boyko, N., & Salabay, B. (2026). Assessing Sales Forecasting Methods: A Comparative Evaluation of Exponential Smoothing Models and SutteARIMA. Applied Computational Intelligence and Soft Computing, 2026(1), 6686245. DOI: https://doi.org/10.1155/acis/6686245

[13] Kumar, L., Khedlekar, S., & Khedlekar, U. K. (2024). A comparative assessment of holt winter exponential smoothing and autoregressive integrated moving average for inventory optimization in supply chains. Supply Chain Analytics, 8, 100084. DOI: https://doi.org/10.1016/j.sca.2024.100084

[14] Kavzoglu, T., & Teke, A. (2022). Predictive performances of ensemble machine learning algorithms in landslide susceptibility mapping using random forest, extreme gradient boosting (XGBoost) and natural gradient boosting (NGBoost). Arabian Journal for Science and Engineering, 47(6), 7367-7385. DOI: https://doi.org/10.1007/s13369-022-06560-8

[15] Natras, R., Soja, B., & Schmidt, M. (2022). Ensemble machine learning of random forest, AdaBoost and XGBoost for vertical total electron content forecasting. Remote Sensing, 14(15), 3547. DOI: https://doi.org/10.3390/rs14153547

[16] Sahin, E. K. (2020). Assessing the predictive capability of ensemble tree methods for landslide susceptibility mapping using XGBoost, gradient boosting machine, and random forest. SN Applied Sciences, 2(7), 1308. DOI: https://doi.org/10.1007/s42452-020-3060-1

[17] Abedi, R., Costache, R., Shafizadeh-Moghadam, H., & Pham, Q. B. (2022). Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees. Geocarto International, 37(19), 5479-5496. DOI: https://doi.org/10.1080/10106049.2021.1920636

[18] Wen, L., Zhou, K., & Yang, S. (2020). Load demand forecasting of residential buildings using a deep learning model. Electric Power Systems Research, 179, 106073. DOI: https://doi.org/10.1016/j.epsr.2019.106073

[19] Rithani, M., Kumar, R. P., & Doss, S. (2023). A review on big data based on deep neural network approaches. Artificial Intelligence Review, 56(12), 14765-14801. DOI: https://doi.org/10.1007/s10462-023-10512-5

[20] Islam, B. U., & Ahmed, S. F. (2022). Short‐term electrical load demand forecasting based on LSTM and RNN deep neural networks. Mathematical Problems in Engineering, 2022(1), 2316474. DOI: https://doi.org/10.1109/TSG.2017.2753802

[21] Liu, Y., Zhang, F., Yang, S., & Cao, J. (2023). Self-attention mechanism for dynamic multi-step ROP prediction under continuous learning structure. Geoenergy Science and Engineering, 229, 212083. DOI: https://doi.org/10.1016/j.geoen.2023.212083

[22] Hernández, A., & Amigó, J. M. (2021). Attention mechanisms and their applications to complex systems. Entropy, 23(3), 283. DOI: https://doi.org/10.3390/e23030283

[23] Zhu, Q., Han, J., Chai, K., & Zhao, C. (2023). Time series analysis based on informer algorithms: A survey. Symmetry, 15(4), 951. DOI: https://doi.org/10.3390/sym15040951

[24] Yang, X., Li, H., Huang, X., & Feng, X. (2024). FEDAF: frequency enhanced decomposed attention free transformer for long time series forecasting. Neural Computing and Applications, 36(26), 16271-16288. DOI: https://doi.org/10.1007/s00521-024-09937-y

[25] Shen, N., Li, H., Bai, Y., Yang, X., & He, R. (2024, October). Combining Fourier-Based Channel Attention with TCN and Informer for Railway Accident Prediction. In 2024 Global Reliability and Prognostics and Health Management Conference (PHM-Beijing) (pp. 1-8). IEEE. DOI: https://doi.org/10.1109/phm-beijing63284.2024.10874650

[26] Jiao, T., Guo, C., Feng, X., Chen, Y., & Song, J. (2024). A comprehensive survey on deep learning multi-modal fusion: Methods, technologies and applications. Computers, Materials & Continua, 80(1). DOI: https://doi.org/10.32604/cmc.2024.053204

[27] Qiao, Y., Yang, R., Liu, Y., Chen, J., Zhao, L., Huo, P., ... & Zhao, Y. (2024). DeepFusion: A deep bimodal information fusion network for unraveling protein-RNA interactions using in vivo RNA structures. Computational and Structural Biotechnology Journal, 23, 617-625. DOI: https://doi.org/10.1016/j.csbj.2023.12.040

[28] Glebova, E., & Madsen, D. Ø. (2024). Twin transformation as a strategic approach in sport management: the synergy of digitalization and sustainability in sports. Frontiers in Sports and Active Living, 6, 1403793. DOI: https://doi.org/10.3389/fspor.2024.1403793

[29] Zhou, H., & Xiong, Z. (2025). Navigating the digital frontier: inherent mechanisms, challenges, and strategies for sports consumption upgrade in the digital economy. Journal of the Knowledge Economy, 16(2), 8687-8726. DOI: https://doi.org/10.1007/s13132-024-02005-9

[30] Wei, H., & Zhang, Y. (2025). Research on the digital transaction model of the sports industry chain based on blockchain technology. Scientific Reports, 15(1), 25131. DOI: https://doi.org/10.1038/s41598-025-10045-7

[31] Liu, J., Zhu, S., Wang, Z., & Chen, S. (2024). The evolution of online public opinion on earthquakes: a system dynamics approach. Humanities and Social Sciences Communications, 11(1), 1636. DOI: https://doi.org/10.1057/s41599-024-04162-3

[32] Guo, Q., Zhao, X., Ba, J., & Luo, C. (2025). Porosity prediction with Bi-LSTM network for deep methane reservoirs. Journal of Seismic Exploration, 34(6), 29–44. DOI: https://doi.org/10.36922/JSE025410087

[33] Zhang, W., Zhang, J., Huang, Z., Yu, J., Feng, D., & Wang, S. (2025). Predicting channel sandstone thickness through a VIF-NRBO-XGBoost model. Journal of Seismic Exploration, 34(3), 1–12. DOI: https://doi.org/10.36922/JSE025290037