DLPAL Software: What You Can Do With It

There are three versions of DLPAL software: DLPAL S, DLPAL PRO and DLPAL LS. Below is a brief account of what you can do with the three different versions of DLPAL

Deep Learning Price Action Lab™ (DLPAL) is based on a proprietary deep learning 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 analysis1. 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.

DLPAL S

DLPAL S is a two-month fully function trial of DLPAL that identifies parameter-less strategies in historical price data that fulfill user-defined performance statistics and risk/reward parameters. These strategies are also known as price patterns. 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 clusters3. Then, the program uses the extracted features in supervised learning mode to identify strategies and systems of strategies that fulfill the user objectives. DLPAL S generates code for strategies and systems for the Quantopian platform, Tradestation (EasyLanguage), Multicharts (EasyLanguage), NinjaTrader 7 and Amibroker AFL.

In 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. 

Click here to download the free trial4.

DLPAL PRO

DLPAL PRO has all the capabilities of DLPAL S but it also allows for extraction of a substantially larger feature set5. This version offers three main functions: Search, Scan and P-Indicator.

Search is used to search for strategies in historical data of any timeframe. The strategies can be grouped into systems. These strategies are also known as price patterns. 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 clusters3. Then, the program uses the extracted features in supervised learning mode to identify strategies and systems of strategies that fulfill the user objectives. DLPAL S generates code for strategies and systems for the Quantopian platform, Tradestation (EasyLanguage), Multicharts (EasyLanguage), NinjaTrader 7 and Amibroker AFL

In 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. 

Scan can be used as a scanner to determine whether there are strategies that fulfill the user-defined criteria as of the close of the most recent bar in historical data. The difference between search and scan is that the latter finds only those strategies that fulfill the user-defined criteria as of the most recent bar. Robustness and portfolio backtests can be used to validate the strategies.

P-Indicator calculates a number of high quality features based on price action. The features can be used as an indication of the probability of the direction of price in the short-term. The p-indicator output of DLPAL has been used by fund managers around the world with machine learning algorithms, such as Support Vector Machines, to identify short term opportunities in the markets, including long/short market neutral strategies.

Click here to download the free trial4.

DLPAL LS

DLPAL LS includes an extended version of the p-indicator function of DLPAL PRO. This program is used to develop algorithmic and machine learning strategies for directional and long/short trading6. Users of the program can sort results based on different criteria and generate output for trading APIs. Historical files of features can be generated for backtesting the strategies.

Click here for an example and here for more details and for information on requesting a free trial.

Examples

For articles with examples using all three versions of DLPAL click here.

Free trials

Click here to request free trials.

Notes

1. If a data-mining method exhibits stochasticity by generating different results each time it runs with same data and parameters then it cannot be cross-validated. 

2. Monte Carlo simulation is not available because it is not an appropriate method when trading strategies are determined from the data and for this reason it can generate misleading results.

3. DLPAL does not use pre-programmed strategies as it is the case with some other commercial programs that work based on a database of patterns they apply on each case. DLPAL determined patterns from price action. 

4. DLPAL S is absolutely free for two months. The program user can generate unlimited strategies and test them in the platforms the program generates code for. 

5. DLPAL S can identify strategies from up to 6 bars. DLPAL PRO goes up to 9 bars and as a result the feature set substantially increases. In addition, DLPAL PRO offers a number of choices of feature sub-clusters not available in DLPAL S. 

6. DLPAL LS is available only to hedge funds.

Disclaimer

This entry was posted in Quantitative trading and tagged , , . Bookmark the permalink.

Leave a Reply