This study applies large language models (LLMs) to measure technological links and examines its predictive power in the Chinese stock market. Using the BAAI General Embedding (BGE) model, we extract semantic information from patent textual data to construct the technological momentum measure. As a comparison, the measure based on traditional International Patent Classification (IPC) is also considered. Empirical analysis shows that both measures significantly predict stock returns and they capture complementary dimensions of technological links. Further investigation through stratified analysis reveals the critical role of investor inattention in explaining their differential performance: in stocks with low investor inattention, IPC-based measure loses its predictive power while BGE-based measure remains significant, indicating that straightforward information is fully priced in while complex semantic relationships require greater cognitive processing; in stocks with high investor inattention, both measures exhibit predictability, with BGE-based measure showing stronger effects. These findings support behavioral finance theories suggesting that complex information diffuses more slowly in markets, especially under significant cognitive constraints, and demonstrate LLMs’ advantage in uncovering subtle technological connections that traditional methods overlook.

In this paper we use the data from “paipaidai”, an online peer-to-peer lending platform in China, to testify whether mood affects the efficiency of credit approval by individual. Refering to the studies in Psychology and Financial Economics, we employ season, temperature and weather as mood proxies, and crotrol the variables related to the quality of loan to study the credit approval behavior under different mood condition. The results suggest that the efficiency of credit approval is significantly correlated with mood—positive mood would improve the efficiency, while negative mood would reduce it. Specifically, loan examined under better mood condition (e.g. spring, comfortable temperature, and sunny days) has significantly higher probability of approval, but lower probability to default if approved; and that examined under lower mood condition shows lower probability of approval and higher probability to default if approved. This effect of mood is even stronger when a loan application to judge is more complex, atypical, or unusual. Moreover, investor sentiment, denoted by closed-end fund premiums, has the same effect on credit approval as well.