Multi-factor investment strategy based on ChatGPT and deep learning algorithm in new energy automobile industry

As a major emerging industry in the world, the new energy vehicle industry is undergoing rapid development and change. Since its development in 2009, China's new energy automobile industry has accumulated a certain first-mover advantage and scale advantage, and at present, China has the largest number of new energy automobile brands and automobile manufacturers in the world. As the rise of the technology industry and the development of the capital market are closely related, the global capital market's expectation of the development of the new energy automobile industry is also reflected in the securities market. Coupled with the rapid development of Internet information technology, quantitative investment programs based on artificial intelligence have great potential for future development in the financial field. In this paper, we propose a machine learning quantitative trading strategy that takes into account both the sentiment factor and the historical trading data of the financial market. The main role of ChatGPT is to propose and explain different investment strategies by combining the information collected during the market research and analysis phase. This strategy combines two different deep learning models, Natural Language Processing NLP and Time Series Processing LSTM, to extract multidimensional quantitative factors and construct a balanced machine learning based quantitative multi-factor investment strategy for equities. The single-factor strategy is synthesized and compared with the proposed novel multi-factor strategy with equal strategy parameter configurations. The proposed multifactor synthesized strategy is able to achieve higher returns as well as maintain moderate retracement and Sharpe ratios, which outperforms other existing strategies.