Tag Archives: Machine generation of trading systems
Forward performance testing is considered the third and often the final stage before employing a trading system in actual trading. The first two stages usually involve the in-sample and out-of-sample testing. This is a report of the forward performance of trading systems for … Continue reading
The SPY2p5 system, which was generated by Price Action Lab on April 7, 2012, outperformed the market in 2012 by a wide margin.
The introduction of a delay in the entry of a position after a price pattern is formed can under certain circumstances act as a filter of price corrections that often follow. In the absence of a delay, positions may suffer an immediate … Continue reading
In this example of machine generation of trading systems, the steps are presented for discovering price patterns with a high reward-risk ratio for SPY using the Price Action Lab search function. The in-sample results are tested on a portfolio of ETFs and also cross-validated in an out-of-sample to eliminate … Continue reading
It is easy for trading system developers to be fooled by randomness especially when the underline process that is used for discovering the trading systems is in itself inherently random. Out-of-sample testing is not enough to guarantee statistical significance of any results obtained because … Continue reading
This is a report of the forward performance of machine designed trading strategies for SPY, QQQ and DIA using Price Action Lab. We call “forward performance” the results obtained for the systems after the end of the out-of-sample period used during the development phase. These … Continue reading