SPADE-LSTM: An Integrated Sequential Pattern Mining and Deep Learning for Badminton Next-Stroke Prediction

Jefita Resti Sari; Sachnaz Desta Oktarina; Erfiani Erfiani

doi:10.59395/ijadis.v7i1.1510

Authors

Jefita Resti Sari Master Program in Statistics and Data Science, School of Data Science, Mathematics and Informatics, IPB University
Sachnaz Desta Oktarina Master Program in Statistics and Data Science, School of Data Science, Mathematics and Informatics, IPB University
Erfiani Erfiani Master Program in Statistics and Data Science, School of Data Science, Mathematics and Informatics, IPB University

DOI:

https://doi.org/10.59395/ijadis.v7i1.1510

Keywords:

Badminton, Stroke Pattern, Prediction, SPADE, LSTM

Abstract

Badminton rallies consist of complex and rapid stroke transitions that reflect players’ tactical decision-making. While prior studies have examined stroke patterns descriptively or applied standalone predictive models, limited research integrates interpretable sequential pattern mining with deep learning for next-stroke prediction. This study proposes an integrated SPADE–LSTM framework to analyze and predict badminton stroke sequences using a 10-class scheme (drive, dropshot, lob, netting, and smash for two athletes). Match data were transformed into structured stroke sequences and contextual features, then divided into training, validation, and test sets using a match–set–rally grouping strategy to prevent information leakage. Sequential patterns were first extracted using the Sequential Pattern Discovery using Equivalent Classes (SPADE) algorithm to capture frequent tactical transitions. These pattern-based features were subsequently used to train a Long Short-Term Memory (LSTM) model for multi-class classification. The proposed model achieved an accuracy of 88.68%, with weighted precision, recall, and F1-score of 0.9075, 0.8868, and 0.8851, respectively. Misclassifications were mainly observed in tactically similar stroke transitions and minority classes. The results indicate that integrating interpretable sequential pattern mining with deep learning provides both strong predictive performance and meaningful tactical insights for badminton performance analysis.

1356 741

Downloads

Download data is not yet available.

Author Biographies

Jefita Resti Sari, Master Program in Statistics and Data Science, School of Data Science, Mathematics and Informatics, IPB University

Department Master of Statistic and Data Sains, School of Data Science, Mathematics and Informatics, IPB University
Sachnaz Desta Oktarina, Master Program in Statistics and Data Science, School of Data Science, Mathematics and Informatics, IPB University

Department Master of Statistic and Data Sains, School of Data Science, Mathematics and Informatics, IPB University
Erfiani Erfiani, Master Program in Statistics and Data Science, School of Data Science, Mathematics and Informatics, IPB University

Department Master of Statistic and Data Sains, School of Data Science, Mathematics and Informatics, IPB University

References

[1] J. R. Sari and A. Ahdika, Modeling the Badminton Stroke Pattern Through the Sequential Pattern Discovery Using Equivalent Classes (SPADE) Algorithm, Mendel, vol. 29, no. 1, pp. 3744, Jun. 2023, doi: 10.13164/mendel.2023.1.037. DOI: https://doi.org/10.13164/mendel.2023.1.037

[2] D. Cabello Manrique and J. J. Gonzlez-Badillo, Analysis of the characteristics of competitive badminton, Br. J. Sports Med., vol. 37, no. 1, pp. 6266, 2003, doi: 10.1136/bjsm.37.1.62. DOI: https://doi.org/10.1136/bjsm.37.1.62

[3] E. Edmizal et al., Biomechanical Analysis of Smash Stroke in Badminton: A Comparative Study of Elite and Recreational Players: a systematic review, Retos, vol. 57, pp. 809817, 2024, doi: 10.47197/retos.v57.107662. DOI: https://doi.org/10.47197/retos.v57.107662

[4] G. Laffaye, M. Phomsoupha, and F. Dor, Changes in the Game Characteristics of a Badminton Match: A Longitudinal Study through the Olympic Game Finals Analysis in Men s Singles, vol. 1992, no. January, pp. 584590, 2015.

[5] Y. Zhao, A. Zhu, S. Zhang, and Y. Zhang, Comparison of the temporal and technical-tactical characteristics in badminton men s singles under different competition formats, no. September, 2025, doi: 10.3389/fpsyg.2025.1634776. DOI: https://doi.org/10.3389/fpsyg.2025.1634776

[6] R. Green, A. T. West, and M. E. T. Willems, Notational Analysis and Physiological and Metabolic Responses of Male Junior Badminton Match Play, 2023. DOI: https://doi.org/10.3390/sports11020035

[7] R. Agrawal, H. Mannila, R. Srikant, H. Toivonen, and a I. Verkamo, Fast discovery of association rules, 1996. [Online]. Available: http://www.cs.helsinki.fi/hannu.toivonen/pubs/advances.pdf

[8] M. J. Zaki, SPADE: An efficient algorithm for mining frequent sequences, Mach. Learn., vol. 42, no. 12, pp. 3160, 2001, doi: 10.1023/A:1007652502315. DOI: https://doi.org/10.1023/A:1007652502315

[9] D. A. Saputra, E. T. Tosida, S. I. Komputer, and U. Pakuan, Penentuan Pola Sekuensial Data Transaksi Penjualan menggunakan Algorimta Sequential Pattren Discovery using Equivalent Classes (SPADE) (Diki Andika S, Eneng Tita T, Fajar Delli W), vol. 16, no. 2, 2019, [Online]. Available: https://journal.unpak.ac.id/index.php/komputasi271 DOI: https://doi.org/10.33751/komputasi.v16i2.1621

[10] A. Noah, R. Intan, and A. N. Tjondrowiguno, Menggunakan SPADE Algorithm Untuk Sistem Rekomendasi Film, J. INFRA, vol. 8, no. 1, 2020.

[11] S. K. Fillah and D. Rahman Prehanto, Sequential Pattern Mining Data Pemeriksaan Pasien Menggunakan Algoritma SPADE (Sequential Pattern Using Discovery Equivalent Classes) Studi Kasus BPI Albasrah Wajak, Jeisbi, vol. 03, no. 1, pp. 917, 2022. DOI: https://doi.org/10.26740/jeisbi.v3i1.44059

[12] W. W. T. Fok, L. C. W. Chan, and C. Chen, Artificial intelligence for sport actions and performance analysis using Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM), ACM Int. Conf. Proceeding Ser., pp. 4044, 2018, doi: 10.1145/3297097.3297115. DOI: https://doi.org/10.1145/3297097.3297115

[13] T. Fernando, S. Denman, S. Sridharan, and C. Fookes, Memory augmented deep generative models for forecasting the next shot location in tennis, IEEE Trans. Knowl. Data Eng., vol. 32, no. 9, pp. 17851797, 2020, doi: 10.1109/TKDE.2019.2911507. DOI: https://doi.org/10.1109/TKDE.2019.2911507

[14] Q. Zhang, X. Zhang, H. Hu, C. Li, Y. Lin, and R. Ma, Sports match prediction model for training and exercise using attention-based LSTM network, Digit. Commun. Networks, vol. 8, no. 4, pp. 508515, 2022, doi: 10.1016/j.dcan.2021.08.008. DOI: https://doi.org/10.1016/j.dcan.2021.08.008

[15] L. Xiaoyan, R. C. Raga, and S. Xuemei, GloVe-CNN-BiLSTM Model for Sentiment Analysis on Text Reviews, J. Sensors, vol. 2022, 2022, doi: 10.1155/2022/7212366. DOI: https://doi.org/10.1155/2022/7212366

[16] W. Wang, T. Ik, N. Yang, and M. Chiao, ShuttleSet: A Human-Annotated Stroke-Level Singles Dataset for Badminton Tactical Analysis, 2022, doi: 10.1145/3580305.3599906. DOI: https://doi.org/10.1145/3580305.3599906

[17] W.-Y. Wang, H.-H. Shuai, K.-S. Chang, and W.-C. Peng, ShuttleNet: Position-aware Fusion of Rally Progress and Player Styles for Stroke Forecasting in Badminton, 2021. DOI: https://doi.org/10.1609/aaai.v36i4.20341

[18] S. K. Dini, M. N. Aidi, and B. Sartono, Sequential pattern mining of rawi hadis (Case study: Shahih hadis of Imam Bukhari from software Ensiklopedi Hadis Kitab 9 Imam), AIP Conf. Proc., vol. 1827, no. 2017, 2017, doi: 10.1063/1.4979446. DOI: https://doi.org/10.1063/1.4979446

[19] R. KRIBII and Y. FAKIR, Mining Frequent Sequential Patterns, J. BIG DATA Res., vol. 1, no. 2, p. 20, 2021, doi: https://doi.org/10.14302/issn.2768-0207.jbr-21-3455. DOI: https://doi.org/10.14302/issn.2768-0207.jbr-21-3455

[20] R. Bunker, K. Fujii, H. Hanada, and I. Takeuchi, sport to identify important patterns of play: an application, pp. 119, 2021.

[21] V. K. R. Chimmula and L. Zhang, Time series forecasting of COVID-19 transmission in Canada using LSTM networks, Chaos, Solitons and Fractals, vol. 135, 2020, doi: 10.1016/j.chaos.2020.109864. DOI: https://doi.org/10.1016/j.chaos.2020.109864

[22] R. Wesley and R. Gunawan, LITERATUR REVIEW: METODE DEEP LEARNING UNTUK ANALISIS TEKS, vol. 8, no. 5, pp. 1102011023, 2024. DOI: https://doi.org/10.36040/jati.v8i5.11780

[23] Y. Imrana, Y. Xiang, L. Ali, and Z. Abdul-Rauf, A bidirectional LSTM deep learning approach for intrusion detection, Expert Syst. Appl., vol. 185, no. July, p. 115524, 2021, doi: 10.1016/j.eswa.2021.115524. DOI: https://doi.org/10.1016/j.eswa.2021.115524

[24] S. Hochreiter and J. Schmidhuber, Long Short-Term Memory, Neural Comput., vol. 9, no. 8, pp. 17351780, 1997, doi: 10.1162/neco.1997.9.8.1735.

[25] S. Hochreiter and J. Schmidhuber, Long short-term memory. Neural Com- putation, vol. 9(8), pp. 17351780, 1997. DOI: https://doi.org/10.1162/neco.1997.9.8.1735

[26] R. C. Staudemeyer and C. W. Omlin, Evaluating performance of long short-term memory recurrent neural networks on intrusion detection data, pp. 218224, 2013. DOI: https://doi.org/10.1145/2513456.2513490

[27] T. T. H. Le, J. Kim, and H. Kim, An Effective Intrusion Detection Classifier Using Long Short-Term Memory with Gradient Descent Optimization, 2017 Int. Conf. Platf. Technol. Serv. PlatCon 2017 - Proc., no. February, 2017, doi: 10.1109/PlatCon.2017.7883684. DOI: https://doi.org/10.1109/PlatCon.2017.7883684

[28] K. N. Khikmah, Kajian Kinerja Multiple Long Short-Term Memory Untuk Analisis Data Deret Waktu Takstasioner, Institut Pertanian Bogor, 2024.

[29] B. Krawczyk, Learning from imbalanced data: open challenges and future directions, Prog. Artif. Intell., vol. 5, no. 4, pp. 221232, 2016, doi: 10.1007/s13748-016-0094-0. DOI: https://doi.org/10.1007/s13748-016-0094-0

[30] M. Buda, A. Maki, and M. A. Mazurowski, A systematic study of the class imbalance problem in convolutional neural networks Mateusz, pp. 249259, 2018. DOI: https://doi.org/10.1016/j.neunet.2018.07.011

[31] M. N. Razali, N. Arbaiy, and P. Lin, Optimizing Multiclass Classification Using Convolutional Neural Networks with Class Weights and Early Stopping for Imbalanced Datasets, pp. 114, 2025. DOI: https://doi.org/10.3390/electronics14040705

[32] J. Davis et al., Methodology and evaluation in sports analytics: challenges, approaches, and lessons learned, Mach. Learn., vol. 113, pp. 66777010, 2024, doi: https://doi.org/10.1007/s10994-024-06585-0. DOI: https://doi.org/10.1007/s10994-024-06585-0

[33] G. Cynthia and A. Qoiriah, Klasifikasi Tingkat Kesiapan Kerja Mahasiswa Universitas Negeri Surabaya Menggunakan Algoritma C5.0, J. Informatics Comput. Sci., vol. 6, no. 02, pp. 383396, 2024, doi: 10.26740/jinacs.v6n02.p383-396. DOI: https://doi.org/10.26740/jinacs.v6n02.p383-396

[34] M. Grandini, E. Bagli, and G. Visani, METRICS FOR MULTI-CLASS CLASSIFICATION: AN OVERVIEW, Statistics (Ber)., pp. 117, 2020, doi: 10.48550/arXiv.2008.05756.

[35] M. Sokolova and G. Lapalme, A systematic analysis of performance measures for classification tasks, Inf. Process. Manag., vol. 45, no. 4, pp. 427437, 20009, doi: https://doi.org/10.1016/j.ipm.2009.03.00. DOI: https://doi.org/10.1016/j.ipm.2009.03.002