EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

DeepHits: A Multimodal CNN Approach to Hit Song Prediction

Michael Nofer, Valdrin Nimani, Oliver Hinz

Machine Learning and Knowledge Extraction · 2026-03-02 · 8 (3) · 58

DOI: 10.3390/make8030058 ↗

At a glance

Journal article in Machine Learning and Knowledge Extraction, published online on 2026-03-02. Written by Michael Nofer and 2 co-authors. 31 references. The full text is freely available (open access, CC BY 4.0).

AbstraktBibliografické údajeCiteRelated studies

Abstract (original language)

Hit Song Science aims to forecast a song’s success before release and benefits from integrating signals beyond audio content alone. We present DeepHits, an end-to-end multimodal network that combines (i) log-Mel spectrogram embeddings from a compact residual 2D-CNN, (ii) frozen multilingual BERT lyric embeddings, and (iii) structured numeric features including high-level Spotify audio descriptors and contextual metadata (artist popularity, release year). Evaluated on 92,517 tracks from the SpotGenTrack dataset, DeepHits achieves a macro-F1 of 52.20% (accuracy 82.63%) in the established three-class setting and a macro-F1 of 23.15% (accuracy 37.00%) in a ten-class decile benchmark. To contextualize fine-grained performance, we report capacity-controlled shallow baselines, including metadata-only and early/late fusion variants, and show that the deep multimodal model provides a clear gain over these references (e.g., metadata-only: macro-F1 20.92%; accuracy 34.22%). Ablation results indicate that removing metadata yields the largest degradation in class-balanced performance, highlighting the strong predictive value of artist popularity and release year. Overall, DeepHits provides a reproducible benchmark and modality analysis for fine-grained popularity prediction under class imbalance.

Cite

APA

Nofer, M., Nimani, V., & Hinz, O. (2026). DeepHits: A Multimodal CNN Approach to Hit Song Prediction. Machine Learning and Knowledge Extraction, 8(3), 58. https://doi.org/10.3390/make8030058

Vancouver

Nofer M, Nimani V, Hinz O. DeepHits: A Multimodal CNN Approach to Hit Song Prediction. Machine Learning and Knowledge Extraction. 2026;8(3):58. doi:10.3390/make8030058

BibTeX
@article{Nofer2026,
  author = {Nofer, Michael and Nimani, Valdrin and Hinz, Oliver},
  title = {DeepHits: A Multimodal CNN Approach to Hit Song Prediction},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {3},
  pages = {58},
  doi = {10.3390/make8030058}
}
Start for free →