AI Predictions, Strategic Disclosure, and Optimal Coarse Bracketing
How to cite
Yi, Junjian; Li, Yan; Han, Xu. 2026. "AI Predictions, Strategic Disclosure, and Optimal Coarse Bracketing." AEA RCT Registry. AEARCTR-0018400. https://doi.org/10.1257/rct.18400-1.0
Download: BibTeX · RIS — for reference managers without a browser translator. Zotero and most others pick up this page's citation metadata directly.
* Primary investigator
Abstract
This study examines how the presentation of delivery-time predictions affects user behavior and satisfaction on a large digital logistics platform. Online platforms often provide estimated delivery times, but these predictions are inherently uncertain. Platforms must decide how precisely to present this information—for example, as a specific time, a broader time window, or with additional shipment checkpoint updates. In collaboration with a large logistics information platform, we conduct a randomized controlled field experiment in which users are randomly assigned to different versions of the shipment-tracking interface. The experiment varies three main dimensions: the type of prediction model used, whether intermediate shipment nodes are displayed, and the precision of the predicted delivery time. The study aims to understand how information precision and algorithmic framing influence user beliefs, query behavior, satisfaction, and engagement. In particular, we examine whether more precise predictions improve user experience, whether coarser information increases repeated checking behavior, and how these trade-offs affect short-run platform revenue and long-run user retention. The findings will contribute to research on information design, behavioral responses to uncertainty, and the economic implications of AI-supported digital services.
Intervention
Participants will be exposed to different versions of a package-tracking interface on a digital logistics platform. The intervention consists of randomized variation in how predicted delivery information is presented to users.
The study varies three dimensions of the interface:
1. Prediction model type:
Users are assigned to different prediction systems, including a traditional statistical prediction model, a higher-accuracy AI-based model, a faster but lower-cost AI model, or a baseline non-model estimate.
2. Information display structure
Users are randomly assigned to either view only the final predicted delivery time or view additional intermediate shipment checkpoint information during the delivery process.
3. Time precision of prediction
The estimated delivery time is displayed at different levels of precision, including day-level, 6-hour window, 1-hour window, or 30-minute window.
After the initial randomized assignment, users may choose to adjust the displayed precision level according to their own preference. These choices are recorded as part of the study. The intervention is embedded in the platform’s normal shipment-tracking service and does not affect the actual delivery process.
Experimental design
This study is a large-scale randomized field experiment embedded in the shipment-tracking interface of a digital logistics platform. The experiment uses a multi-arm factorial design that varies three dimensions of the user interface and prediction system:
Prediction model type (4 arms)
Users are assigned to one of four prediction approaches: a traditional model, a high-accuracy AI model, a fast AI model, or a baseline non-model estimate.
Intermediate shipment information (2 arms)
Users are randomly assigned to either view intermediate shipment checkpoint information or only the final estimated delivery time.
Prediction time precision (4 arms)
Estimated delivery times are displayed at one of four levels of precision: day-level, 6-hour window, 1-hour window, or 30-minute window.
These three dimensions generate a factorial treatment structure with multiple treatment combinations. Eligible users are randomly assigned at first exposure to one treatment condition by the platform’s backend experimental system.
After the initial assignment, users may choose to adjust the displayed precision level according to their own preferences. This feature allows the study to observe both the causal effects of default information presentation and users’ endogenous preferences for information granularity. The intervention affects only the presentation of predictive information and does not alter the actual logistics or delivery process.
Design details
Cited by
No citation data available for this registration yet.