In recent years, machine learning for trading has become the buzz-word for many quant firms. In their quest to seek the elusive alpha, a number of funds and trading firms have adopted to machine learning. This post gives a brief overview of the development of machine learning and its growing importance for quants and traders alike.
Machine Learning gains popularity in Algorithmic TradingMachine learning techniques can be applied to trading using programming languages like Python, R, C++ etc. Machine learning packages/libraries are developed in-house by firms for their proprietary use or by third parties who make it freely available to the user community. In recent years, the number of machine learning packages has increased substantially which has helped the developer community in accessing various machine learning techniques and applying the same to their trading needs.
Source: kdnuggets.com. There are hundreds of ML algorithms, these algorithms can be classified into different types depending on how these work. For example, machine learning regression algorithms are used to model the relationship between variables; decision tree algorithms construct a model of decisions and are used in classification or regression problems (Machine Learning: An Introduction to Decision Trees). Of these, some algorithms have become popular among quants. Some of these include:
- Linear Regression
- Logistic Regression
- Random Forests (RM)
- Support Vector Machine (SVM)
- k-Nearest Neighbor (kNN)
- Classification and Regression Tree (CART)
- Deep learning
- Analyzing historical market behavior using large data sets
- Determine optimal inputs (predictors) to a strategy
- Determining the optimal set of strategy parameters
- Making trade predictions etc.
Resources to Study Machine LearningKeeping oneself updated is of prime importance in today’s world. Professional quants and traders who intend to expand their knowledge can take up machine learning courses (part-time or full-time) which are offered by some well-known institutes. This can help enhance their career or provide them additional tools in the development of trading strategies for themselves or their firms.
Here’s a blog on ML resources - Free Resources to Learn Machine Learning for Trading
Other Research AreasMachine learning techniques are applied in various markets like equities, derivative, Forex, etc. Machine learning enthusiast/Quants/Traders who intend to apply machine learning techniques to trading should also have some know-how on related subjects like Programming, Basic statistics, Market microstructure, Sentiment analysis, Technical analysis etc.
Machine Learning CompetitionsThere are a number of sites which host ML competitions. These competitions although not specifically targeted towards the application of ML in trading, can give good exposure to quants and traders to different ML problems via participation in competitions & forums and help expand their ML knowledge. Some of the popular ML competition hosting sites include:
- kaggle - (https://www.kaggle.com/)
- NUMERAI - (https://numer.ai/)
- Topcoder - (https://www.topcoder.com/)
- CrowdAnalytics - (https://www.crowdanalytix.com/)
- DrivenData - (https://www.drivendata.org/)
Funds using Machine Learning TechniquesSome established funds like Medallion fund, Citadel, D.E. Shaw are said to be using machine learning techniques for trading. However, the extent to which these ML techniques are applied in trading remains unknown to outsiders, and so does the contribution of machine learning strategies in the overall performance of these funds.
There are some hedge funds that have revealed extensive use of machine learning techniques as part of their core strategy. For example, Taaffeite Capital Management (http://taaffeitecm.com/). Taaffeite Capital trades in a fully systematic and automated fashion using proprietary machine learning systems. Here is a list of funds and trading firms that are using artificial intelligence or machine learning.