Causal Graph Fuzzy LLMs: A First Introduction and Applications in Time Series Forecasting

In recent years, the application of Large Language Models (LLMs) to time series forecasting (TSF) has garnered significant attention among researchers. This study presents a new frame of LLMs named CGF-LLM using GPT-2 combined with fuzzy time series (FTS) and causal graph to predict multivariate time series, marking the first such architecture in the literature. The key objective is to convert numerical time series into interpretable forms through the parallel application of fuzzification and causal analysis, enabling both semantic understanding and structural insight as input for the pretrained GPT-2 model. The resulting textual representation offers a more interpretable view of the complex dynamics underlying the original time series. The reported results confirm the effectiveness of our proposed LLM-based time series forecasting model, as demonstrated across four different multivariate time series datasets. This initiative paves promising future directions in the domain of TSF using LLMs based on FTS.

Setting Players' Behaviors in World of Warcraft through Semi-Supervised Learning

Digital games are one of the major and most important fields on the entertainment domain, which also involves cinema and music. Numerous attempts have been done to improve the quality of the games including more realistic artistic production and computer science. Assessing the player's behavior, a task known as player modeling, is currently the need of the hour which leads to possible improvements in terms of: (i) better game interaction experience, (ii) better exploitation of the relationship between players, and (iii) increasing/maintaining the number of players interested in the game. In this paper we model players using the basic four behaviors proposed in \cite{BartleArtigo}, namely: achiever, explorer, socializer and killer. Our analysis is carried out using data obtained from the game "World of Warcraft" over 3 years (2006 $-$ 2009). We employ a semi-supervised learning technique in order to find out characteristics that possibly impact player's behavior.