Performance Development Planning

We love researching new methods and adapting them to the ever changing market landscape.

Read more

Quantitative Research and Development

Understanding market behaviour is our prerequisite in delivering robust and efficient quantitative models.

Read more

International Business Opportunities

We are currently looking for partners and investors that are willing to join us in our quest for expansion and upbeat profitability.

Read more
About Us

We are a group of quants developing algorithmic trading systems using behavioral finance concepts enhanced by machine learning elements. 

Our team of researchers develops scientific work in the field of quantitative finance with a main focus on Pattern Recognition, Jump Detection, Event Studies and Media Mining.

The vision we follow is unique as we are combining both academic and traders/investors approaches in the attempt to fit in the pieces of the financial markets complex puzzle. Grasping and leveraging on market core principles is our drive in reading through the data and spotting opportunities.

We create algorithmic trading systems specially designed to leverage systematic big data models, taking advantage of a significant database of historical data that includes public news streams, technical analysis and proprietary data flows.

We look forward to doing great things with you
anywhere in the world.

Our Research

The Scientific Laboratory stands at the root of Beyond Market Noise products with the mission to generate analyses that are the result of a combination of three types of experiences achieved by its members: Trading, Programming and Academic Research.

Pattern Recognition in Price Chart: A survey
Pattern Recognition
Pattern Recognition and future (unexpected) Jumps
Pattern Recognition
The event study methodology
Scheduled Event
How relevant is the relevance criterion on economi...
Scheduled Event
Chinese macroeconomic data
Scheduled Event
What trigger jumps? Negative versus Positive jumps
Jump Identification
Periodicity in Intraday log-returns
Jump Identification
Non-parametric Daily and Intradaily Tests
Jump Identification
Measures of Realized Variance
Jump Identification
Reasoning and Purpose
Jump Identification

Request a call back