Evaluation on interactive waiting experience design of mobile internet products based on machine learning

Yi YuScientific 2023 · DOI

Abstract

In today's rapidly changing economy, efficient lifestyle has become the current situation of most mobile product users. With the development of performance tools and technologies, a fast lifestyle has brought more wealth and opportunities to users. The slow pace and fluctuating time are indirect income losses, which cause user anxiety to some extent. When the waiting time exceeds the user's waiting threshold, users would experience negative emotions, such as boredom, anxiety and anger, and product satisfaction would drop significantly. Therefore, by analyzing the uniqueness of mobile Internet products and the characteristics of users, this paper studied the reasons and influencing factors of product interactive waiting, and then used machine learning algorithm to analyze the cost function of interactive waiting experience. Finally, the corresponding interactive waiting experience design strategy was proposed. By comparison, the user experience after product interaction optimization design was 8.4% higher than that before product interaction optimization design, and the user frequency was also 14.7% higher after optimization design. In short, user experience plays an important role in product interaction design.

The Problem: The Psychological Gap in Waiting

In our "fast lifestyle" economy, every second a mobile app spends loading is perceived as an indirect income loss or a source of anxiety. When waiting times exceed a user’s internal threshold, satisfaction plummets, leading to boredom, anger, and eventually, app abandonment.

The core challenge is the mismatch between hardware performance and data-heavy software requirements. While developers often focus on technical optimization, this paper addresses the psychological gap: the difference between actual physical waiting time (objective) and how long the user feels they have been waiting (subjective).

Conceptual framework of physical vs. psychological waiting time factors

Methodology and Machine Learning Cost Function

The author treats the waiting experience as a mathematical optimization problem. The primary technical contribution is the development of a cost function for interactive waiting, derived through machine learning principles:

  1. Asymmetric Probability ($a_{ij}$): The model calculates the probability of waiting based on the Euclidean distance between maximum and minimum waiting times, using a Gaussian kernel to account for variance in user experience.
  2. Gaussian Neighborhood ($b_{ij}$): This represents the waiting probability within a specific "neighborhood" of similar user descriptions.
  3. The Cost Function ($T$): By comparing these two probability distributions (using a formula reminiscent of Kullback-Leibler divergence), the author quantifies the "cost" of the waiting experience.

Based on this foundation, the paper proposes five design strategies: optimizing loading feedback, alleviating anxiety via micro-content, offering alternative "lite" solutions, psychological compensation (high-value moments post-wait), and user-centric personalization.

Experimental Results

The study involved 150 users across three product categories: smartphones, sports watches, and heart rate collectors. The experimental results showed a significant "dominant difference" (p < 0.05) between traditional design and the ML-optimized design.

Quantitative comparison of waiting time and feedback effects across test products

Key performance metrics post-optimization included:

  • User Experience Score: Increased by 8.4%.
  • User Stickiness: The frequency of app use rose by 14.7%.
  • Waiting Time Proportion: The proportion of time users spent "waiting" relative to total interaction dropped from an average of 0.23 to 0.07.
  • Cost Function Reduction: The ML cost function value (representing user friction) dropped from an initial 0.58 to 0.12 over a five-day optimization period.

Conclusion

Waiting should not be viewed as a technical gap, but as a specific phase of interaction requiring its own design logic. By providing agency and feedback, developers can bridge the psychological gap and improve user satisfaction. Future work suggests moving toward "predictive loading"—using ML to anticipate user actions and load data before the user even clicks, potentially eliminating the "waiting" state entirely.

Summary updated

Abstract

In today's rapidly changing economy, efficient lifestyle has become the current situation of most mobile product users. With the development of performance tools and technologies, a fast lifestyle has brought more wealth and opportunities to users. The slow pace and fluctuating time are indirect income losses, which cause user anxiety to some extent. When the waiting time exceeds the user's waiting threshold, users would experience negative emotions, such as boredom, anxiety and anger, and product satisfaction would drop significantly. Therefore, by analyzing the uniqueness of mobile Internet products and the characteristics of users, this paper studied the reasons and influencing factors of product interactive waiting, and then used machine learning algorithm to analyze the cost function of interactive waiting experience. Finally, the corresponding interactive waiting experience design strategy was proposed. By comparison, the user experience after product interaction optimization design was 8.4% higher than that before product interaction optimization design, and the user frequency was also 14.7% higher after optimization design. In short, user experience plays an important role in product interaction design.
BibTeX
@inproceedings{yu2023evaluation,
  author = {Yi Yu},
  title = {{Evaluation on interactive waiting experience design of mobile internet products based on machine learning}},
  booktitle = {Scientific},
  year = {2023},
  doi = {10.1038/s41598-023-43405-2},
}
Figure