Deep Learning Price Action Lab (DLPAL) identifies strategies in historical price data that fulfill user-defined performance statistics and risk/reward parameters. The program uses primitive attributes of price action, and specifically the open, high, low and close, to extract features types in an unsupervised learning mode based on general feature clusters. Then, the program uses the extracted features in supervised learning mode to identify strategies and systems of strategies that fulfill the user objectives. This procedure is outlined below:
DLPAL is used to search for strategies in historical data of any timeframe. The strategies can be grouped into systems. The program can generate strategy and system code for a number of popular trading platforms. For the daily timeframe, the system tracking module of the program can be used to monitor signal generation of the strategies and systems going forward in time and as new data are available. DLPAL is a meta-system that discovers trading systems.
Deep Learning Price Action Lab generates code for strategies and systems for the Quantopian platform, Tradestation (EasyLanguage), Multicharts (EasyLanguage), NinjaTrader 7, 8 and Amibroker AFL.
Development and upgrade history
DLPAL S was based on DLPAL that in turn was based on a program originally developed by Michael Harris in 2010. The most important changes in DLPAL were an optimization of the deep learning algorithm, the addition of a progress monitor that can warn the user if program execution must be aborted, among other things and a change in terminology to comply with advances in quantitative trading and machine learning. DLPAL S is a reduced version of DLPAL that allows generating unlimited strategies based on parameter-less price action features, also called price patterns in technical analysis.
DLPAL S v1.0 Released May 1, 2017.
DLPAL S v2.0 released June 19, 2017
– Search algo improvement
– Different tabs to show equity and trades in backtesting and Test Strategies
– Improved Test Files tool
DLPAL S v2.5 released March 8, 2018
– Added option to sort by win rate P in Portfolio backtest
– Test Files checks for files with invalid delimiters and lists only files with zero values
– Added option to abort and save results of search up to that pont. Program must be closed and then Open Last must be used to recover results.
DLPAL S v3.0 released March 18, 2019
– Changed results layout
– Portfolio Backtest and Robustness Test results are appended to original results
– Selections from Portfolio Backtest and Robustness tests can be saved
– Improved sorting of results
– Profit factor values greater than 100 are set to 100 to allow sorting
– Four equal partitions of Extended cluster are now available for faster searches
– Starting with this version the help file is available only online and in pdf form
– Minor bug fixes and algorithm improvements
DLPAL S v3.0 update released September 8, 2020
– Minor fixes
– Improved search algo