Use in trading
As of 2014, more than 75 percent of the stock shares traded on United States exchanges (including the New York Stock Exchange and NASDAQ) originate from automated trading system orders.ATSs can be designed to trade stocks,options, futures and foreign exchange products based on a predefined set of rules which determine when to enter an order, when to exit a position and how much money to invest in each trading product. Trading strategies differ; some are designed to pick market tops and bottoms, others to follow a trend, and others involve complex strategies including randomizing orders to make them less visible in the marketplace.
Back-testing of a trading system involves programmers running the program using historical market data in order to determine whether the underlying algorithm guiding the system may produce the expected results. Developers can create back-testing software to enable a trading system designer to develop and test their trading systems using historical market data to optimize the results obtained with the historical data. Although back-testing of automated trading systems cannot accurately determine future results, an automated trading system can be back-tested using historical prices to see how the system theoretically would have performed if it had been active in a past market environment.
Forward testing of an algorithm can also be achieved using simulated trading with real-time market data to help confirm the effectiveness of the trading strategy in the current market and may be used to reveal issues inherent in the computer code.
