Learning When to Quit in Sales Conversations
This addresses inefficiencies in high-volume outbound sales by correcting cognitively-bounded human decisions to improve salesforce efficiency, though it is incremental as it applies existing methods to a new domain.
The paper tackles the problem of when salespeople should quit unproductive sales conversations by developing a language model-based stopping agent that learns to imitate an optimal stopping policy. The agent reduces time spent on failed calls by 54% while preserving sales, increasing expected sales by up to 37% when applied to telecom call data.
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.