Machine Learning Approaches for Predicting Song Popularity: A Case ‎Study in Music Analytics

  • Authors

    • Uppuluri Lakshmi Soundharya Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India
    • Sasidhar Reddy Gaddam Staff IT Software Engineer, Palo Alto Networks, Huntersville, North Carolina, USA
    • Gogineni Krishna Chaitanya Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India
    • T. L. Deepika Roy Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, India
    • Uppuluri Naga Lakshmi Madhuri Department of Computer Science and Engineering NRI Institute of Technology Pothavarapadu, Andhra Pradesh, India
    https://doi.org/10.14419/gjywez76

    Received date: May 19, 2025

    Accepted date: June 21, 2025

    Published date: July 10, 2025

  • Music Popularity Prediction; Machine Learning; XGBoost; LightGBM; Predictive Modeling; Feature Engineering; ‎Hyperparameter Optimization; Data Analytics; Comparative Analysis; Song Characteristics; Genre Classification; ‎Ensemble Models; Cross-Validation; Optuna; Data Pre-processing; Feature Importance; Regression; Music Analytics‎.

  • Abstract

    Comprehending the aspects that impact song popularity has become crucial in the ever-changing music industry. This ‎study explores the field of music popularity predictive modeling using the cutting-edge algorithms XGBoost and ‎LightGBM. Predictive models were developed by the study using a large dataset that includes a variety of musical variables, ‎such as song duration, tempo, lyrical content, and release year. To improve the models' predictive capacity, the study ‎approach includes extensive work. To provide a thorough assessment of the algorithms' performance, the dataset is ‎divided into training and testing sets. Additionally, the effectiveness of XGBoost and LightGBM forecasting music ‎popularity is evaluated by a comparison analysis. To increase the prediction models' accuracy, hyperparameter ‎optimization methods—specifically, Optuna—are used to fine-tune them. In addition, the study looks at feature ‎importance, illuminating elements of music that, in the eyes of each algorithm, greatly add to its appeal. Using a rigorous ‎cross-validation approach, the models are validated, and their generalization capabilities are shown. The performance ‎metrics, which provide a comprehensive picture of the models' predicted accuracy, include mean absolute error, mean ‎squared error, median absolute error, and R-squared. By providing a comparative analysis of two well-known machine ‎learning methods for forecasting music popularity, this paper advances the rapidly developing field of music analytics. The ‎results offer significant perspectives for professionals in the field and data scientists who are looking for efficient ‎approaches to forecast music popularity across various genres‎.

  • References

    1. aneria, Adit V., et al. "Prediction of Song Popularity Using Machine Learning Concepts." Smart Sensors Measurements and Instrumentation: Select Proceedings of CISCON 2020. Springer Singapore, 2021 https://doi.org/10.1007/978-981-16-0336-5_4.
    2. Chiru, Costin, and Oana-Georgiana Popescu. "Automatically determining the popularity of a song." Rough Sets: International Joint Conference, IJCRS 2017, Olsztyn, Poland, July 3–7, 2017, Proceedings, Part I. Springer International Publishing, 2017 https://doi.org/10.1007/978-3-319-60837-2_33.
    3. Raza, Agha Haider, and Krishnadas Nanath. "Predicting a Hit Song with Machine Learning: Is there an apriori secret formula?" 2020 International Conference on Data Science, Artificial Intelligence, and Business Analytics (DATABIA). IEEE, 2020. https://doi.org/10.1109/DATABIA50434.2020.9190613.
    4. Ni, Yizhao, et al. "Hit song science once again a science." 4th International Workshop on Machine Learning and Music. 2011.
    5. Kamal, Jigisha, et al. "A Classification-Based Approach to the Prediction of Song Popularity." 2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES). IEEE, 2021. https://doi.org/10.1109/ICSES52305.2021.9633884.
    6. Arora, Shruti, Rinkle Rani, and Nitin Saxena. "Music Stream Analysis for the Prediction of Song Popularity using Machine Learning and Deep Learning Approach." 2022 3rd International Conference on Computing, Analytics and Networks (ICAN). IEEE, 2022. https://doi.org/10.1109/ICAN56228.2022.10006843.
    7. Dong, Aoran, Ruizhe Qiu, and Zhen Ye. "Regression Analysis of Song Popularity based on Ridge, K-Nearest Neighbors and Multiple-Layers Neural Networks." Highlights in Science, Engineering and Technology 39 (2023): 609-617. https://doi.org/10.54097/hset.v39i.6602.
    8. Vötter, Michael, et al. "Novel datasets for evaluating song popularity prediction tasks." 2021 IEEE International Symposium on Multimedia (ISM). IEEE, 2021. https://doi.org/10.1109/ISM52913.2021.00034.
    9. Reiman, Minna, and Philippa Örnell. "Predicting hit songs with machine learning." (2018).
    10. Saragih, Harriman Samuel. "Predicting song popularity based on spotify's audio features: insights from the Indonesian streaming users." Journal of Management Analytics (2023): 1-17. https://doi.org/10.1080/23270012.2023.2239824.
    11. Lee, Junghyuk, and Jong-Seok Lee. "Music popularity: Metrics, characteristics, and audio-based prediction." IEEE Transactions on Multimedia 20.11 (2018): 3173-3182. https://doi.org/10.1109/TMM.2018.2820903.
    12. Anjana, S. A Robust Approach to Predict the Popularity of Songs by Identifying Appropriate Properties. Diss. 2021.
    13. Zhao, Siyuan. "Popular Song Recommendation Program Based on Machine Learning Algorithm." 2021 3rd International Conference on Artificial Intelligence and Advanced Manufacture. 2021. https://doi.org/10.1145/3495018.3495478.
    14. Jabade, Vaishali, Vedang Deshpande, and K. Aditya. "Music generation and song popularity prediction using artificial intelligence-an overview." International Journal of Computer Application 182.50 (2019): 33-39. https://doi.org/10.5120/ijca2019918762.
    15. Vötter, Michael, et al. "Song Popularity Prediction using Ordinal Classification." (2023).
    16. Luo, Kehan. "Machine Learning Approach for Genre Prediction on Spotify Top Ranking Songs." (2018).
    17. Mayerl, Maximilian, et al. "Pairwise learning to rank for hit song prediction." (2023).
    18. Pachet, François, and Pierre Roy. "Hit Song Science Is Not Yet a Science." ISMIR. 2008.
    19. Interiano, Myra, et al. "Musical trends and predictability of success in contemporary songs in and out of the top charts." Royal Society open science 5.5 (2018): 171274. https://doi.org/10.1098/rsos.171274.
    20. Nikas, Dionisios, and Dionisios N. Sotiropoulos. "A Machine Learning Approach for Modeling Time-Varying Hit Song Preferences." 2022 13th International Conference on Information, Intelligence, Systems & Applications (IISA). IEEE, 2022. https://doi.org/10.1109/IISA56318.2022.9904376.
    21. Essa, Yasmin, et al. "Predicting Song Popularity Using Machine Learning Algorithm." (2022).
    22. Holst, Gustaf, and Jan Niia. "Song Popularity Prediction with Deep Learning: Investigating predictive power of low-level audio features." (2023).
    23. Yang, Li-Chia, et al. "Revisiting the problem of audio-based hit song prediction using convolutional neural networks." 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). IEEE, 2017. https://doi.org/10.1109/ICASSP.2017.7952230.
    24. Pham, James, Edric Kyauk, and Edwin Park. "Predicting song popularity." Dept. Comput. Sci., Stanford Univ., Stanford, CA, USA, Tech. Rep 26 (2016).
    25. Wang, Tao. "Classification and Popularity Assessment of English Songs Based on Audio Features."
    26. Dhanaraj, Ruth, and Beth Logan. "Automatic Prediction of Hit Songs." Ismir. 2005.
    27. Reisz, Niklas, Vito DP Servedio, and Stefan Thurner. "To what extent homophily and influencer networks explain song popularity." arXiv preprint arXiv:2211.15164 (2022).
    28. Carroll, Conor. Commercialism in Popular Music: Analysing brand mentions in song lyrics. Using Machine Learning to create lyrics in the style of different genres: Technical Report. Diss. Dublin, National College of Ireland, 2021.
    29. Jakubowski, Kelly, et al. "Dissecting an earworm: Melodic features and song popularity predict involuntary musical imagery." Psychology of Aesthetics, Creativity, and the Arts 11.2 (2017): 122. https://doi.org/10.1037/aca0000090.
    30. Merritt, Sean H., Kevin Gaffuri, and Paul J. Zak. "Accurately predicting hit songs using neurophysiology and machine learning." Frontiers in Artificial Intelligence 6 (2023): 1154663. https://doi.org/10.3389/frai.2023.1154663.
    31. Huang, Liusuo, and Yan Song. "Intangible Cultural Heritage Management Using Machine Learning Model: A Case Study of Northwest Folk Song Huaer." Scientific Programming 2022 (2022). https://doi.org/10.1155/2022/1383520.
    32. Song, Yang, et al. "Investigating sense of place of the Las Vegas Strip using online reviews and machine learning approaches." Landscape and Urban Planning 205 (2021): 103956. https://doi.org/10.1016/j.landurbplan.2020.103956.
    33. Chen, Yi-Wei, Qingquan Song, and Xia Hu. "Techniques for automated machine learning." ACM SIGKDD Explorations Newsletter 22.2 (2021): 35-50. https://doi.org/10.1145/3447556.3447567.
    34. Xin, Doris, et al. "How Developers Iterate on Machine Learning Workflows--A Survey of the Applied Machine Learning Literature." arXiv preprint arXiv:1803.10311 (2018).
    35. Song, Congzheng, Thomas Ristenpart, and Vitaly Shmatikov. "Machine learning models that remember too much." Proceedings of the 2017 ACM SIGSAC Conference on computer and communications security. 2017. https://doi.org/10.1145/3133956.3134077.
    36. Xu, Jing, et al. "Comprehensive assessment of machine learning-based methods for predicting antimicrobial peptides." Briefings in Bioinformatics 22.5 (2021): bbab083. https://doi.org/10.1093/bib/bbab083.
    37. Álvarez, P., J. García de Quirós, and S. Baldassarri. "RIADA: A Machine-Learning Based Infrastructure for Recognising the Emotions of Spotify Songs." (2023). https://doi.org/10.9781/ijimai.2022.04.002.
    38. Cueva Mora, Alan, and Brendan Tierney. "Feature Engineering vs Feature Selection vs Hyperparameter Optimization in the Spotify Song Popularity Dataset." (2021).
    39. Zheng, Liqiong, et al. "Monitor concrete moisture level using percussion and machine learning." Construction and Building Materials 229 (2019): 117077. https://doi.org/10.1016/j.conbuildmat.2019.117077.
    40. Yuan, Jiuchuang, et al. "Virtual coformer screening by a combined machine learning and physics-based approach." CrystEngComm 23.35 (2021): 6039-6044. https://doi.org/10.1039/D1CE00587A.

  • Downloads

  • How to Cite

    Soundharya , U. L. ., Gaddam, S. R. . ., Chaitanya, G. K. . ., Roy , T. L. D. ., & Madhuri , U. N. L. . (2025). Machine Learning Approaches for Predicting Song Popularity: A Case ‎Study in Music Analytics. International Journal of Basic and Applied Sciences, 14(2), 711-720. https://doi.org/10.14419/gjywez76