Research on the Construction and Performance Optimization of a Deep Learning-Driven Price Prediction Model for E-Sports Hotels

This paper explores the construction of a deep learning-driven price prediction model for e-sports hotels to address the complexity of price forecasting in the e-sports hotel market. The study compares traditional time series prediction models with deep learning models, particularly the Long Short-Term Memory (LSTM) networks, emphasizing the advantages of deep learning in handling nonlinear patterns and sequential data. By employing a model fusion strategy, the LSTM model is combined with the autoregressive integrated moving average (ARIMA) model to enhance prediction performance and stability. The research also examines factors influencing e-sports hotel prices, including user behavior, market environment, and e-sports equipment configuration, and involves data preprocessing, model construction, and performance optimization. Experimental results show that the proposed ARIMA-LSTM model performs well in terms of prediction accuracy and interpretability, providing a scientific basis for pricing strategies in e-sports hotels.