Announcing The Release of DLPAL v1.0

We are pleased to announce the release of DLPAL v1.0, a software program for short-term systematic and discretionary traders that can identify anomalies in price action via the use of proprietary unsupervised and supervised machine learning algorithms.

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. Below is an outline of the DLPAL machine learning process:


Note that feature extraction from basic attributes of price action (O, H, L, C) is not a trivial process and although some think they have accomplished it with naive means, including basic neural networks and genetic programming, in reality they have not. DLPAL uses a proprietary algorithm for unsupervised feature extraction that goes much beyond naive machine learning and data-mining.

The next step in the development of DLPAL will involve generation of data files for use with Python machine learning pipeline. These files will include continuous and discrete attribute values and will allow implementation of a wide variety of trading strategies for traders and hedge funds, such as long/short equity trading, pair trading and arbitrage of a number of other anomalies in price action.

Note: All orders for a license of DLPAL received this month (October 2016) will get a free upgrade to v2.0 when it is released.

Instructions for downloading a demo

More information about DLPAL

Sales pitch

Identifying and exploiting anomalies in price action fast is the key to profitable trading. DLPAL is another tool that can assist traders to accomplish this difficult task.

Disclaimer Please read before ordering.

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

Leave a Reply