CoChat

Advanced customer churn prediction for a music streaming digital marketing service using attention graph-based deep learning approach

Open access
Cheng, Haiyan, He, Jie · 2025 · Scientific Reports

The DOI matches its Crossref record; 31 of the 33 references it cites were found in a registry or an index, and 2 are not checked yet.

Abstract

Customer churn poses a persistent threat to the sustainability of music streaming platforms, where user disengagement often occurs unpredictably. Most existing churn prediction methods fail to integrate relational dependencies among users or address the limitations of static, tabular models in imbalanced datasets. In this research, we propose a Hybrid Graph Attention Network (Hybrid GAT + MLP (Multi Layered Perceptron)) that efficiently combines graph-based learning with deep tabular feature modelling, allowing the capture of both individual behaviour and peer-influenced churn patterns. The use of a synthetic similarity graph enables the model to learn from neighbourhood context, while a weighted loss function ensures robustness against class imbalance without altering data distribution. The model was evaluated on the KKBox dataset, achieving an accuracy of 95.8% with an AUC score of 0.9626, indicating high discriminative power. Additional metrics, such as F1-score, confusion matrix, and ROC analysis, ensure the system’s ability to generalize across both churn and non-churn classes. These results validate the applicability of our approach to large-scale, real-world scenarios involving churn detection. All code and the curated dataset for customer churn prediction for music steaming is available at the https://github.com/haiyanchenas/Advanced-Customer-Churn-Prediction-for-a-Music-Streaming-Digital-Marketing-Service/tree/main enabling reproducibility of our findings.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41598-025-28357-z

Cites

31 of 33 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Proposed hybrid churn detection workflow.
Fig. 1 Proposed hybrid churn detection workflow.CC BY-NC-ND · PubMed Central
Fig. 2 Log CSV statistical data distribution.
Fig. 2 Log CSV statistical data distribution.CC BY-NC-ND · PubMed Central
Fig. 3 Member csv statistical data distribution.
Fig. 3 Member csv statistical data distribution.CC BY-NC-ND · PubMed Central
Fig. 4 Transaction csv statistical data distribution and pie chart –train CSV data analysis.
Fig. 4 Transaction csv statistical data distribution and pie chart –train CSV data analysis.CC BY-NC-ND · PubMed Central
Fig. 5 Distribution plots of key engineered features used for churn prediction: (a) membership duration in days, (b) log-transformed total listening time, (c) capped subscription cancellation count, and (d) total subscription transactions.
Fig. 5 Distribution plots of key engineered features used for churn prediction: (a) membership duration in days, (b) log-transformed total listening time, (c) capped subscription cancellation count, and (d) total subscription transactions.CC BY-NC-ND · PubMed Central
Fig. 6 Impact of Z-score standardisation on the \:membership\_days feature.
Fig. 6 Impact of Z-score standardisation on the \:membership\_days feature.CC BY-NC-ND · PubMed Central
Fig. 7 Detailed architecture of the proposed hybrid model.
Fig. 7 Detailed architecture of the proposed hybrid model.CC BY-NC-ND · PubMed Central
Algorithm 1 The proposed churn detection algorithm.
Algorithm 1 The proposed churn detection algorithm.CC BY-NC-ND · PubMed Central
Fig. 8 Final confusion matrix for the Hybrid GAT + MLP model on the KKBox test set.
Fig. 8 Final confusion matrix for the Hybrid GAT + MLP model on the KKBox test set.CC BY-NC-ND · PubMed Central
Fig. 9 Training loss and accuracy curves demonstrating stable convergence and high generalization performance of the Hybrid GAT + MLP model.
Fig. 9 Training loss and accuracy curves demonstrating stable convergence and high generalization performance of the Hybrid GAT + MLP model.CC BY-NC-ND · PubMed Central
Fig. 10 ROC curve showing strong classification performance of the Hybrid GAT + MLP model with an AUC of 0.9583 on the KKBox test set.
Fig. 10 ROC curve showing strong classification performance of the Hybrid GAT + MLP model with an AUC of 0.9583 on the KKBox test set.CC BY-NC-ND · PubMed Central
Fig. 11 Precision-recall curve of the hybrid GAT + MLP model.
Fig. 11 Precision-recall curve of the hybrid GAT + MLP model.CC BY-NC-ND · PubMed Central
Fig. 12 Top 15 most important features for churn prediction ranked by Gini impurity.
Fig. 12 Top 15 most important features for churn prediction ranked by Gini impurity.CC BY-NC-ND · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 33 references

Research works printed but not linked: 3

  1. Joy, U. G., Hoque, K. E., Uddin, M. N., Chowdhury, L. & Park, S. B. A big data-driven hybrid model for enhancing streaming service customer retention through churn prediction integrated with explainable AI. IEEE Access. (2024).
  2. Fujo, S. W., Subramanian, S. & Khder, M. A. Customer churn prediction in telecommunication industry using deep learning. Inf. Sci. Lett. 11(1), 24 (2022).
  3. Panimalar, S. A. & Krishnakumar, A. A review of churn prediction models using different machine learning and deep learning approaches in cloud environment. J. Curr. Sci. Technol. 13(1), 136–161 (2023).

Cited by

See all 5

Metadata

Authors
Cheng, H., & He, J.
Affiliations
Nanchang University (CN)
Corresponding author
Cheng, Haiyan
Venue
Scientific Reports
Published
2025-12-20
Volume
15
Issue
1
Pages
45028-45028
ISSN
2045-2322 (ISSN-L)
OpenAlex
W4417522567
Cited by
1
References
31
Citations by year
2026: 1
FWCI
1.74
Type
journal article
Language
en
Open access
Licence
Locations
  • Scientific Reports (publishedVersion, cc-by-nc-nd)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by-nc-nd)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Social Sciences › Business, Management and Accounting › Marketing › Customer churn and segmentation
  • Social Sciences › Business, Management and Accounting › Marketing › Customer Service Quality and Loyalty
  • Social Sciences › Business, Management and Accounting › Organizational Behavior and Human Resource Management › AI and HR Technologies
Keywords
customer churn prediction, music streaming platforms, graph attention networks, multilayer perceptron, class imbalance, weighted loss function, peer influence, user disengagement, digital marketing

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Advanced customer churn prediction for a music streaming digital marketing service using attention graph-based deep learning approach. https://app.cochat.ai/papers/10.1038/s41598-025-28357-z
The paper
Cheng, H., & He, J. (2025). Advanced customer churn prediction for a music streaming digital marketing service using attention graph-based deep learning approach. Scientific Reports. https://doi.org/10.1038/s41598-025-28357-z

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.