Research on the Construction and Dynamic Optimization of a Quantitative Investment Model Based on LSTM-ElasticNet Hybrid Architecture
Yuanchen Wang · CREATIVE ECONOMY · 2025
With the explosive growth of financial market data and the significant improvement in computing power, the application of deep learning technology in the field of quantitative investment has gradually attracted attention. This paper aims to construct a deep learning-based quantitative investment model that achieves precise capture of stock market investment opportunities by integrating multiple financial factors and deep learning algorithms. The paper first introduces the basic concepts of quantitative investment and the current status of deep learning applications in the financial field. It then elaborates on the construction process of the deep learning-based quantitative investment model, including data preprocessing, feature engineering, model training, and optimization. Through empirical analysis, the effectiveness of the model in stock market investment is verified, and the performance differences of different deep learning algorithms are compared. The research results show that deep learning models can significantly enhance the return performance and risk control capabilities of quantitative investment strategies, providing new research directions and practical tools for the field of quantitative investment.