Learning When to Quit in Sales Conversations

2025-11-02

AI Summary

This study addresses the dynamic screening decision problem of “when to terminate unproductive dialogues” in high-frequency outbound sales calls. Methodologically, we propose the first learnable optimal stopping framework—“Stop Agent”—which models high-dimensional textual dialogue states using generative language models (GLMs), integrates counterfactual reasoning and sequential decision-making techniques, and imitates human optimal abandonment strategies from real call transcripts while identifying and correcting associated cognitive biases. Our key contribution is the formalization of sales abandonment decisions as an optimization-ready optimal stopping problem, with deployment compatibility for both open-source and proprietary large language models. Empirical evaluation at a telecommunications enterprise demonstrates a 54% reduction in average duration of failed calls, with negligible loss in sales revenue; after reallocating the saved time, expected sales increase by up to 37%.

Technology Category

• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Stochastic Optimization
• Machine Learning: Online Learning & Bandits

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Salespeople frequently face the dynamic screening decision of whether to persist in a conversation or abandon it to pursue the next lead. Yet, little is known about how these decisions are made, whether they are efficient, or how to improve them. We study these decisions in the context of high-volume outbound sales where leads are ample, but time is scarce and failure is common. We formalize the dynamic screening decision as an optimal stopping problem and develop a generative language model-based sequential decision agent - a stopping agent - that learns whether and when to quit conversations by imitating a retrospectively-inferred optimal stopping policy. Our approach handles high-dimensional textual states, scales to large language models, and works with both open-source and proprietary language models. When applied to calls from a large European telecommunications firm, our stopping agent reduces the time spent on failed calls by 54% while preserving nearly all sales; reallocating the time saved increases expected sales by up to 37%. Upon examining the linguistic cues that drive salespeople's quitting decisions, we find that they tend to overweight a few salient expressions of consumer disinterest and mispredict call failure risk, suggesting cognitive bounds on their ability to make real-time conversational decisions. Our findings highlight the potential of artificial intelligence algorithms to correct cognitively-bounded human decisions and improve salesforce efficiency.

Problem

• Optimizing when to quit sales calls to save time
• Improving real-time conversational decision-making in sales
• Reducing failure prediction errors in high-volume sales conversations

Innovation

• Formalizes sales persistence as optimal stopping problem
• Develops generative language model-based sequential decision agent
• Handles high-dimensional textual states and scales to large models