NEW YORK--(BUSINESS WIRE)--Sep 10, 2019--
Deep Nexus Inc. (Deep Nexus) today announces the launch of its AI-powered predictive analytics for financial markets. The company utilizes deep learning neural networks with time-series data for trading in equities, futures, commodities, and foreign exchange markets.
“Our core approach is to find repeating patterns and anomalies in data and to use these for intra-day trading,” said Chief Executive Officer Kevin M. Riley. “Our technology stack is complete; from collecting incoming data, to generating analytics, through trade execution. It is the emerging hardware and software technologies, especially deep learning, that have made our platform possible.” Riley began experimenting with quantitative trading strategies and neural networks more than 20 years ago. He initiated work on the Deep Nexus technology platform in early 2017.
Simulated historical trading results demonstrate the potential versus a passive portfolio. From January 2016 to May 2019, a sample Deep Nexus portfolio returned 357% versus 61% for the S&P 500 Index. “The historical performance samples have exceeded our expectations,” said Co-Founder Tif Olson. “It has also been fascinating to watch all the layers in the technology stack run in a live trading environment.”
The typical Deep Nexus model trades on an intra-day basis using 1-minute data. Predictive analytics are generated by proprietary Deep Nexus machine learning algorithms. The analytics are coupled to algorithmic trade logic, which executes trades 24 hours per day. The Deep Nexus platform can accommodate any liquid market while the analytics and trading logic can be optimized to target specific performance objectives. The analytics are structured to provide predictions for both direction and magnitude several time-steps into the future, not just a probability of a price moving up or down.
Deep Nexus is positioned to further enhance its platform with alternative data and emergent technologies. “We see potential to add additional data streams — anything with a time-stamp can be included. The key, however, is to have the correct deep learning architecture to work successfully with time-series data,” Riley noted. “We also look forward to adopting the latest hardware to power the expansion of our capabilities.”
About Deep Nexus
Deep Nexus is a technology research and development company specializing in predictive analytics for financial markets. The company uses a multi-disciplinary approach, collaborating with physicists, mathematicians, electrical engineers, computer scientists, and experts in algorithmic trading. The company’s core technologies revolve around deep learning neural networks that utilize time-series data. More information can be found at www.deepnexus.com.
Deep Nexus does not solicit nor make any services available to the general public. None of the information nor any analyses presented are intended to form the basis for any investment decision, and no specific recommendations are intended. This presentation does not constitute investment advice or counsel or solicitation for investment in any security.
CFTC RULE 4.41: Hypothetical or simulated performance results have certain limitations. Unlike an actual performance record, simulated results do not represent actual trading. Also, since the trades have not been executed, the results may have under-or-over compensated for the impact, if any, of certain market factors, such as lack of liquidity. Simulated trading programs in general are also subject to the fact that they are designed with the benefit of hindsight. No representation is being made that any account will or is likely to achieve profit or losses similar to those shown.
View source version on businesswire.com:https://www.businesswire.com/news/home/20190910005049/en/
CONTACT: Deep Nexus Inc.
Kevin M. Riley, 212 365 4214 (Direct)
KEYWORD: NEW YORK UNITED STATES NORTH AMERICA
INDUSTRY KEYWORD: TECHNOLOGY DATA MANAGEMENT OTHER TECHNOLOGY
SOURCE: Deep Nexus Inc.
Copyright Business Wire 2019.
PUB: 09/10/2019 08:00 AM/DISC: 09/10/2019 08:01 AM