This study aims to improve the predictive ability of financial brand data, help investors and decision-makers better identify different financial brands’ performance, and reduce unnecessary financial risks. The stock prices of various financial brands are undertaken as the experimental objects. The characteristics of financial data and the original model network structure are analyzed based on the Internet of Things (IoT). The long short-term memory (LSTM) neural and the particle swarm optimization algorithm (PSO algorithm) are adopted to optimize the model’s parameters. The autoregressive integrated moving average model (ARIMA) algorithm is used to analyze the spatio-temporal data, and a data prediction model for the financial brand based on the ARIMA-PSO-LSTM algorithm is proposed. In addition, the validity and effectiveness of the proposed model are proved through the analysis and testing of specific example data. It is found that the model based on the IoT shows higher processing speed in contrast to the conventional method; the model proposed in this study shows smaller errors and improved accuracy in data prediction than the PSO-LSTM model and the LSTM model; the model presents better fitting effects and better performance compared with the latest research model. The experimental results reveal that combining the three algorithms can integrate the advantages of various algorithms, and the three algorithms can complement each other, thereby improving the ability of financial data analysis. The model established in this study shows high accuracy and good adaptability in identifying financial brands and predicting financial data.