用技术属性预测用户拥有率，大模型表现优于人类和传统方法
Predicting consumer-technology ownership without a diffusion history
- 用六项感知属性建模，结合约束回归预测技术普及率
- 大模型预测误差比发布年份基准低17%以上，Opus 4.7最优
- 适用于新科技市场趋势预判，尤其适合缺乏历史数据场景
我们检验消费者技术的感知属性是否能预测其普及程度。在2022年对美国成人（n=678）的Prolific调查中，受访者对65种消费技术在六个属性上进行评分。随后，我们从前沿语言模型Anthropic Claude Opus 4.7和OpenAI GPT-5.5获取相同属性评分。通过带符号约束的惩罚回归，以四个UTAUT2接受度属性加对数年龄协变量预测拥有率，并采用逐个技术留出法评估。使用人类评分时，平均绝对误差相比发布年份基线下降17%，而模型表现更优，尤其Opus 4.7效果最佳。在2022至2025年短周期内，由于拥有率变化小，属性模型未能超越无变化基线。我们指出该方法局限性，包括模型评分可能反映已有知识而非独立推理。文中还展示部署案例：对2025与2026年发布的11款产品，预测其2027年拥有率。
原文摘要 · Abstract (English)
We test whether the perceived attributes of a consumer technology predict how widely it is owned. In a 2022 Prolific survey of US adults (n = 678), respondents rated 65 consumer technologies on six attributes. We then elicited the same ratings from two frontier language models, Anthropic Claude Opus 4.7 and OpenAI GPT-5.5. We regress ownership prevalence on four UTAUT2 acceptance attributes plus a log-age covariate with a sign-constrained penalized regression and evaluate it by holding out one technology at a time. The attribute model improves on a baseline of years-since-launch: mean absolute error falls by 17% with the human ratings, and by more with either model, most with Opus 4.7. Over the short 2022-to-2025 window, where ownership moved little, the same attributes do not improve on a no-change baseline. We set out the limitations of the approach, including the possibility that language-model ratings reflect prior knowledge of these technologies rather than independent attribute reasoning. We include a deployment illustration: 2027 ownership predictions for eleven products launched in 2025 and 2026.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。