Metraipolis › archive › dc_0e40abaeb102

CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn Prescription — arXiv:2609.09766

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.09766
License (as archived): CC0-1.0
Archived: 2026-10-16T07:53:19.584Z
SHA-256 of the archived text: c8229235d3788affa2e6550fb7e92cd7012c4367b63f588481727848c17624b2
Stable URL of this page: https://metraipolis.com/documento/dc_0e40abaeb102

How to cite

CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn Prescription — arXiv:2609.09766 — arXiv (en), https://arxiv.org/abs/2609.09766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0e40abaeb102 (Metraipolis archive dc_0e40abaeb102, sha256 c8229235d3788affa2e6550fb7e92cd7012c4367b63f588481727848c17624b2)

BibTeX

@misc{dc0e40abaeb102,
  title = {CARRE: Counterfactual Action Retrieval and Reason Evaluation for Explainable Churn Prescription — arXiv:2609.09766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0e40abaeb102; sha256 c8229235d3788affa2e6550fb7e92cd7012c4367b63f588481727848c17624b2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Churn models typically identify high-risk customers but do not specify which feasible retention action should be considered or why that action is appropriate. We present CARRE (Counterfactual Action Retrieval and Reason Evaluation), a three-stage framework that combines retrieval-augmented candidate generation, cost-aware counterfactual scoring, and large language model (LLM) reasoning. CARRE retrieves a predefined catalog of retention actions, estimates model-predicted churn-risk changes under explicit feature transformations, and generates a structured churn reason and a profile-grounded explanation for the selected action. On the IBM Telco Customer Churn dataset, CARRE achieves 79.8% greater mean model-predicted risk reduction than the plain SHAP baseline and 80.4% greater reduction than the cost-controlled SHAP+Cost baseline across 313 high-risk test cases; its cost-normalized efficiency is 10.5% higher than that of plain SHAP. On a 136-case reason-stratified evaluation sample, diagnosis-driven prompt refinement increases weak-label agreement from 79.4% to 90.4%, with no auxiliary-plan constraint violations; because the same sample was used for error diagnosis and re-evaluation, the post-refinement result is not an independent estimate of generalization. For 135 explanations generated using the pre-refinement v2 reason outputs, two cross-vendor LLM judges assign mean scores ranging from 4.02 to 5.00 out of 5, although one judge saturates on actionability, and a deterministic audit finds no contradictions among 66 verifiable profile claims. Retrieval ablations show that k=5 provides the best evaluated compromise between high candidate coverage and downstream reasoning agreement in this dataset. These results illustrate how retrieval, model-based counterfactual scoring, and language generation can be separated and jointly evaluated in a prototype churn-prescription pipeline.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.09766 — 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 2026-10-16T07:24:00.894Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).