A Survey of AI and Quantitative Finance Methods
Summary
This overview introduces artificial intelligence and machine learning as tools for analyzing financial data and supporting investment decisions or trading operations. It groups methods by task: supervised learning for prediction and classification, unsupervised learning for discovering structure, and reinforcement learning for adaptive strategy development. It also surveys time-series models, including ARIMA, LSTM, and GARCH, alongside deep learning, natural-language processing, and data science techniques.
The discussion extends beyond forecasting to portfolio construction and risk management, naming VaR, expected shortfall, asset allocation, and optimization methods. It also touches on high-frequency trading, market microstructure, arbitrage, and execution algorithms. The material is a broad inventory rather than a practical guide: it gives no implementation details, comparative evidence, or trading results. It notes that methods’ relevance can change with technology and markets, and that suitable choices depend on an investor’s objectives.
Key ideas
- Supervised, unsupervised, and reinforcement learning address different prediction, discovery, and strategy tasks.
- Time-series methods such as ARIMA, LSTM, and GARCH are presented for modeling financial dynamics.
- AI-related quantitative work also includes risk measurement, portfolio optimization, and text-based sentiment analysis.
- Execution, market microstructure, and high-frequency algorithms are included alongside predictive methods.
- The overview gives no empirical comparison or evidence that any listed technique is profitable.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.