Enhancing Financial Market Forecasting with LSTM Networks and Technical Indicators

This paper discusses the application of long short-term memory (LSTM) network in quantitative trading in financial market. It is based on the construction of LSTM model, integrating the moving average (MA), relative strength index (RSI), Bollinger band and other technical indicators, in this way, to achieve the model to enhance the prediction ability of future market trends. This paper divides the data set into three parts:70% for training, 15% for validation, and 15% for testing. The experimental results show that the LSTM model can effectively capture long-term dependencies. Moreover, it performs well on the test data, as the forecast curve closely matches the actual market trend. This method provides a new perspective for theoretical research and practical application, and can be used as an auxiliary decision-making tool for investors and financial institutions to optimize investment strategies, improve investment returns, and promote market stability and sustainable development.