New AI Model CTLNet Outperforms Existing Methods for Shanghai Stock Index Prediction

A new deep learning model called CTLNet has been developed specifically for predicting the Shanghai Composite Index. The model combines CNN, Transformer, and LSTM architectures to leverage their respective strengths in handling multivariate time series data. Researchers note that the Transformer encoder's attention mechanism and parallel processing capabilities are particularly valuable for capturing long sequence dependencies and correlations between different data variables. Comparative experiments demonstrate that CTLNet achieves superior performance compared to current state-of-the-art baseline models. The Shanghai Composite Index prediction represents an area of significant interest for both investors and academic researchers. Deep learning approaches including recurrent neural networks, convolutional neural networks, and transformers have become widely adopted for multivariate time series forecasting tasks. The research was published on arXiv, a platform for sharing scientific papers, under the computer science and artificial intelligence categories.