Metraipolis › archive › dc_78efca3bc83f

PPDL: A Real-world Industrial User Retention Ratio Forecasting Framework Integrating Physical Priors with Deep Learning — arXiv:2609.13789

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.13789
License (as archived): CC0-1.0
Archived: 2026-10-16T00:10:28.549Z
SHA-256 of the archived text: e54c044c4aa20fb7cd0cefea31a161523ab498e25674162c422b5fc707475575
Stable URL of this page: https://metraipolis.com/documento/dc_78efca3bc83f

How to cite

PPDL: A Real-world Industrial User Retention Ratio Forecasting Framework Integrating Physical Priors with Deep Learning — arXiv:2609.13789 — arXiv (en), https://arxiv.org/abs/2609.13789 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_78efca3bc83f (Metraipolis archive dc_78efca3bc83f, sha256 e54c044c4aa20fb7cd0cefea31a161523ab498e25674162c422b5fc707475575)

BibTeX

@misc{dc78efca3bc83f,
  title = {PPDL: A Real-world Industrial User Retention Ratio Forecasting Framework Integrating Physical Priors with Deep Learning — arXiv:2609.13789},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13789},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_78efca3bc83f; sha256 e54c044c4aa20fb7cd0cefea31a161523ab498e25674162c422b5fc707475575},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13789. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In multi-channel paid user acquisition, early and accurate prediction of user retention at the channel level is crucial for optimizing budget allocation. User retention curves display a pronounced temporal pattern: an initial period of high churn transitions into long-term stability. This pattern is further characterized by regular fluctuations attributable to seasonality and exhibits high serial autocorrelation. These intrinsic properties make such curves highly suitable for analysis within a time-series forecasting framework. However, forecasting user retention ratio for large-scale short-video platform faces three major challenges: significant heterogeneity across channels, pronounced global trend of decay followed by saturation, and short look-back windows. To address these challenges, we propose PPDL, a novel forecasting framework that integrates physical priors with deep learning. We first introduce a trend-residual decomposition component. The trend is modeled using the Weibull distribution, whose parameters are learned via a Multilayer Perceptron (MLP). Secondly, for the residual component, we design an auxiliary embedding module on top of a deep learning backbone to maintain the channel identity awareness. Finally, to enhance the model's sensitivity to trends, we design a Multiscale Trend-penalized loss function. The proposed approach PPDL is validated through comprehensive experiments on industrial-scale datasets, covering three applications with an average of 30+ channels each. Experimental results show that PPDL achieves improvements across different backbones and significantly outperforms existing online solutions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.13789 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T23:54:14.639Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).