The Internet of Things (IoT) technology is becoming increasingly pivotal in the financial services sector, with a growing number of algorithms being employed in high-frequency trading. High-frequency prediction in financial time series prediction presents a promising avenue of research. From convolutional neural networks to recurrent neural networks, deep learning have demonstrated exceptional capabilities in capturing the nonlinear characteristics of stock markets, thereby achieving high performance in stock index prediction. In this article, we employ ODE-LSTM model for high-frequency price forecasting, predicting stock price data across various time scales, including 1-, 5-, and 30-min frequencies. This approach introduces a novel concept, wherein the long short-term memory (LSTM) model is integrated with Neural ordinary differential equations (ODEs) to manage the hidden state and augment model interpretability. Over the course of 7 months, we achieved a 41.79% excess return on a simulated trading platform, with a daily average excess return of 0.30%, showcasing the commendable performance of our model and strategy.