Data quality is widely recognized as being directly linked to the quality of analysis results. In this study, we introduce a tagging method that simplifies the handling of extensive data and facilitates the rapid search and extraction of relevant information. Traditional methods that search for and integrate related data from external sources to enrich input data often fail to guarantee the acquisition of desirable information for all data sets. However, the recent advancement of Large Language Models (LLMs) enables the prediction of characteristics of input data, even in the absence of relevant data. In this paper, we present the Generated and Aggregated Tag (GA-Tag), a system that employs LLMs to automatically assign appropriate tags to data and is equipped with an aggregation mechanism to manage tag diversity effectively. The adoption of GA-Tag is anticipated to enhance data analysis and management quality and efficiency, optimize monetary and time costs, and potentially bolster business intelligence and decision-making processes.

Recommendation systems that use auxiliary information such as product names and categories have been proposed to address the cold-start problem. However, these methods do not perform well when we only have insufficient warm-start training data. On the other hand, large language models (LLMs) can perform as effective cold-start recommendation systems even with limited warm-start data. However, they require numerous API calls for inferences, which leads to high operational costs in terms of time and money. This is a significant concern in industrial applications. In this paper, we introduce a new method, RevAug, which leverages LLMs as a data augmentation to enhance cost-efficient cold-start recommendation systems. To generate pseudo-samples, we have reversed the commonly used prompt for an LLM from “Would this user like this item?” to “What kind of items would this user like?”. Generated outputs by this reverse prompt are pseudo-auxiliary information utilized to enhance recommendation systems in the training phase. In numerical experiments with four real-world datasets, RevAug demonstrated superior performance in cold-start settings with limited warm-start data compared to existing methods. Moreover, RevAug significantly reduced API fees and processing time compared to an LLM-based recommendation method.

Topological data analysis (TDA) is an emerging mathematical concept for characterizing shapes in complex data. In TDA, persistence diagrams are widely recognized as a useful descriptor of data, and can distinguish robust and noisy topological properties. This paper proposes a kernel method on persistence diagrams to develop a statistical framework in TDA. The proposed kernel satisfies the stability property and provides explicit control on the effect of persistence. Furthermore, the method allows a fast approximation technique. The method is applied into practical data on proteins and oxide glasses, and the results show the advantage of our method compared to other relevant methods on persistence diagrams.