The full product manual offers a
comprehensive guide for getting familiar with functions and features. The manual is included with the demo version. You can download the manual in pdf or html format:
We strongly recommend reading the manual carefully before testing the demo. In the manual introduction there are tips for quick start and a list of FAQs about data conversions and compatibility with various data formats.
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 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.
There are three versions available: DLPAL S, DLPAL DQ and DLPAL LS.
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 clusters. 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. Several validation methods are available for testing the significance of the results.
has most of the functionality of DLPAL s but for the purposes of an EOD scanner. The program identifies parameter-less strategies in historical
price data that fulfill user-defined performance statistics and risk/reward parameters as of the last bar in the input data files. These strategies are also known
as price patterns. DLPAL DQ generates code for strategies and systems for the Quantopian platform, Tradestation (EasyLanguage), Multicharts
(EasyLanguage), NinjaTrader 7 and Amibroker AFL. It also offers two validation methods.
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 long and short candidates in a
universe of securities. The long/short identification is based on a set of calculated features and the user has flexibility in ranking the results according to their
values. The output of the program can be saved in csv format and can be used in conjunction with trading platforms to automatically execute trades. For more details click
for articles about DLPAL S, DLPAL DQ and DLPAL LS.
Main differences between DLPAL S, DLPAL DQ and DLPAL LS
DLPAL S will identify strategies that fulfill the criteria specified on the search workspace in the whole history of a security, not only those, if any, which form
as of the last bar. Only one security can be specified per search line.Then, the program allows combining any or all of those strategies from the results into
systems and generates code for the systems. It also generates code for each of strategies in the results if that is required. Traders who develop automated strategies choose DLPAL S.
DLPAL DQ will identify strategies that fulfill the criteria specified on a scan workspace as of the last bar in a historical data file only. The user can specify a
directory per scan line and the program will scan all the files for strategies that fulfill the criteria as of the last bar. The user can also specify only one file from
the directory. The program can generate code for the individual strategies in case the user wants to test them in other platforms. Discretionary traders who like
to take into account other indicators too and choose the signals themselves use DLPAL DQ.
DLPAL LS calculates directional probabilities and features for any number of securities as of the last bar in data files and also historical values as of each bar
in historical data files. This program is suitable for developing long/short strategies.
Below is a partial list of the main features of DLPAL. New features will be added in upcoming releases.
Search for strategies and systems of strategies that fulfill user-defined performance criteria and risk/reward parameters.
Search for strategies that are profitable across multiple securities.
Capability of searching for momentum and tick strategies.
Scan for strategies with signals as of the close of the last data bar that fulfill user-defined performance criteria and risk/reward objectives. Multiple symbol
scan capability with multiple risk/reward parameters (DLPAL DQ).
Feature calculations and historical files for use with fixed algos and machine learning (DLPAL LS).
Strategy back, forward and portfolio testing capability, including bulk testing of all strategies in the results.
Strategy Robustness tests.
Search for strategies with trade input delay with automatic optimum delay determination
Strategy database creation and manipulation
Strategy and system code generation for Quantopian platform, Tradestation (EasyLanguage), Multicharts (EasyLanguage), NinjaTrader 7 and Amibroker AFL
Grouping strategies for addition to system tracking. Unlimited number of systems allowed.
Signal tracking of user-defined trading systems saved in system tracking.
Unlimited number of search, scan and p-indicator workspaces with multiple data files and parameters
Intraday strategy search capability
Data conversion utilities and intraday data file conversion
File test and maintenance plus a profitability and position size calculator
Price series statistics, random system simulation and file sample creation functions