Deep Learning Price Action Lab™
Identifying an anomaly in price action before other market participants do
is the key to profitable trading. This is what DLPAL is designed to achieve.
DLPAL can be used with 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 two versions of the software:
- DLPAL DQ is a quantitative scanner for price action anomaly detection. The algo of the program identifies parameter-less strategies formed in historical price data as of the last bar in the input data files that fulfill user-defined performance statistics and risk/reward parameters. Portfolio backtests and robustness test validations methods are available. This program also generates strategy code for Tradestation (EasyLanguage), Multicharts (EasyLanguage), NinjaTrader (7 and 8), and Amibroker AFL. This program can be used by discretionary traders who like to scan many securities each day for price action anomalies and also like to make the final decisions instead of following a system. Click here for more.
- DLPAL LS calculates a set of features that measure the directional bias of a single or group of securities. This version may be useful for both systematic and discretionary equity long/short trading but also directional trading in other markets. The features allow ranking securities according to criteria. The program generates historical values of the features to be used in developing strategies. Click here for more.
- DLPAL S is no longer updated after the last stable version. DLPAL S was designed for trading strategy developers who follow systematic signals. No programming is necessary. DLPAL S generates code for strategies and systems of strategies. Click here for more.
DLPAL versions are based on proprietary algorithms that produce the same output each time they encounter the same market conditions. This determinism and the absence of stochasticity comply 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
A 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 significant strategies is not guaranteed.