Deep Learning Price Action Lab™
Identifying anomalies in price action before other market participants
do is the key to profitable trading. This is what DLPAL is designed to achieve.
DLPAL can identify trading strategies in a variety of markets: Equities, ETFs, commodity futures and even crypto, provided there is a sufficiently long time series of Open, High, Low, Close(*) There are three versions of the software:
- DLPAL S is for trading strategy developers that follow systematic signals. This version identifies parameter-less strategies formed in historical price data that fulfill user-defined performance statistics and risk/reward parameters and generates code for strategies and systems of strategies for the Quantopian platform, Tradestation (EasyLanguage), Multicharts (EasyLanguage), NinjaTrader (7 and 8) and Amibroker AFL. Those interested in developing strategies for systematic trading may use this version. Click here for more.
- DLPAL DQ is a quantitative scanner that identifies parameter-less strategies formed in historical price data that fulfill user-defined performance statistics and risk/reward parameters as of the last bar in the input data files. This version also generates code for strategies and systems for the Quantopian platform, Tradestation (EasyLanguage), Multicharts (EasyLanguage), NinjaTrader (7 and 8) and Amibroker AFL. Discretionary traders that like to scan many securities each day for opportunities and also like to make the final decisions instead of following a system may find this a more appropriate version. Click here for more.
- DLPAL LS calculates a set of features that measure the directional bias of single or group of securities. This version is more appropriate for both systematic and directional equity long/short traders but also directional traders in other markets. The features allow ranking securities according to specific criteria. The reduced functionality version is appropriate for quant discretionary traders and the full version is more appropriate for professional traders and hedge funds that would like to also develop strategies based on the features the program calculates. Click here for more.
DLPAL is based on a proprietary algorithm that produces the same output each time it encounters the same market conditions. This determinism and the absence of stochasticity are in compliance with the standards of scientific testing and analysis. DLPAL minimizes data-mining and data-snooping bias through the use of a proprietary unsupervised learning method for feature extraction and selection. Several functions are available for validation of the results including a randomization tool for ranking the performance of strategies.
New! DLPAL docs
Brief introduction to all versions: DLPAL Software: What You Can Do With It
DLPAL videos: Click here for available videos
*Although DLPAL will work with any Open, High, Low, Close series in any timeframe or even with series with only the Close price after selecting the appropriate cluster, finding statistically significance strategies is not guaranteed.