Cybernetic Trading Strategies: Developing a Profitable Trading System with State-of-the-Art Technologies

19

Machine Learning Methods for Developing Trading Strategies

Machine induction methods extract rules from data. We discussed the theory behind some of these methods in Chapter 11. This chapter gives an overview of how to use machine induction in various trading applications.

Table 19.1 lists some of the ways in which machine induction can be used to develop trading strategies.

The examples given in Table 19.1 use machine induction either to develop or to improve a trading strategy. In the first four examples in the table, the rules developed by the machine induction method are used directly as part of a trading strategy. In the fifth example in the table, the information generated by machine induction helps in selecting which variables are needed to train a neural network with maximum performance and a minimum of architecture.

TABLE 19.1 USES OF MACHINE INDUCTION.

Developing trading rules.]Extracting rules from a neural network. Combining trading strategies. Developing postprocessing for a neural network. Eliminating inputs for use in other modeling methods such as neural networks.

USING MACHINE INDUCTION FOR DEVELOPING TRADING RULES

The classic use of machine induction is to develop sets of rules that classify a target output based on input variables. We can use machine induction methods to develop trading strategies by developing rules that predict the output class of ...