Newest papers

Next Best Action: Causal Constrained Offline RL for Business Action Targeting

Surya Ramachandiran, Yiming Li, Juan Mancilla-Caceres, Tao Ye, Jun Liu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.26817 · cited by 0 works (OpenAlex) · open-access PDF

German

Nächste Best-Action-Systeme (NBA-Systeme) müssen zwischen Kundeninterventionen (z. B. Rabatte, Promotionen und Lifecycle-Aktionen) auswählen, langfristigen wirtschaftlichen Wert maximieren, komplexe operative Einschränkungen befriedigen und kausalerweise begründet bleiben. Die bestehenden Ansätze fehlen einem strengen Rahmen für die gemeinsame Erfüllung dieser Anforderungen. Wir richten diese Lücke an, indem wir NBA als Constrained Markov Decision Process (CMDP) formulieren. Wir integrieren dann die Off-Policy-Konzentrationskurve der geschätzten Kundendynamik direkt in die Formulierung von Linear Space Programming (LP) des CMDP. Die resultierende Politik wählt Maßnahmen basierend auf den Kundenzuständen aus,

Machine translation (Meta M2M100); the English original follows.

Abstract

Next Best Action (NBA) systems must select among customer interventions (e.g., discounts, promotions, and lifecycle actions), maximize long-term economic value, satisfy complex operational constraints, and remain causally grounded. Existing approaches lack a rigorous framework for meeting these requirements jointly. We address this gap by formulating NBA as a Constrained Markov Decision Process (CMDP). We then integrate off-policy causal correction of the estimated customer dynamics directly into the Linear Programming (LP) formulation of the CMDP. The resulting policy selects actions based on customer states to maximize long-term value while explicitly enforcing business guardrails. Furthermore, the LP formulation yields shadow prices that quantify the economic trade-offs of operational constraints (e.g., fairness and user welfare), enhancing policy interpretability. We validate our proposed offline Reinforcement Learning (RL) framework on an industry case study involving rideshare coupon targeting, where customer states are defined by Recency, Frequency, and Monetary (RFM) stages. We evaluate performance using model-based off-policy evaluation, with causal dynamics estimated from a temporal holdout. Under the observed coupon budget and RFM state representation, our optimized policy improves customer lifetime value (LTV) by 19% over the estimated behavior policy and 8% over a myopic baseline. Although the demonstrated action space is binary, the proposed framework is action-agnostic, yielding a general-purpose decision module for targeting systems that manage multiple interventions.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Markov decision process, Computer science, Reinforcement learning, Markov process, State space, Operations research

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange