Our AI Platform

Staying ahead of the game

We have developed an AI-assisted, patent-pending approach to help maintain long-term stable alpha contribution in investment products.

The key differentiator is our proprietary, cutting-edge AI Platform, which automates the invention process of investment strategies and trading models.

With that, we can generate unique Alpha Add-Ons, often tailor-made for specific requirements, in an industrial-like fashion. What usually takes months in development we can compress into mere days with our AI Platform.

This enables our clients to stay ahead of the game, fight alpha decay, improve their products, and protect their assets.

Get in Touch
Artificial Intelligence vs Machine Learning

Artificial Intelligence vs Machine Learning

Although Artificial Intelligence (AI) and Machine Learning (ML) are often used interchangeably, they mean quite different things. AI is a broad catch-all term that describes the ability of a machineusually a computer systemto act intelligently. In contrast, ML is the study of the algorithms and methods that enable computers to solve specific tasks without being explicitly instructed how and instead doing so by identifying persistent relevant patterns within the observed data.

We employ AI and ML for a vast number of tasks.

Ultimately, AI/ML-based strategies can benefit investors in two ways: diversification of portfolios, and reduction of risk.

Keeping in mind the investment management industry’s struggle to adapt to chaotic markets disrupted by topics like the Coronavirus pandemic and wars, the case for investors looking to add non-correlated AI/ML-based alpha sources has never been stronger.

 How is Machine Learning used in investing?

How is Machine Learning used in investing?

Advanced Prediction of Market Movements

Finding of Optimal Positions

Generation of new Features from Data

Validation of Existing Trading Strategies

WHAT MAKES OUR APPROACH TO AI & ML DIFFERENT?

WHAT MAKES OUR APPROACH TO AI & ML DIFFERENT?

We consider the use of AI and ML for the generation of trading strategies as complementary to the construction of strategies by domain knowledge experts. Both approaches have their unique strengths. Domain knowledge experts can generalize their knowledge about one domain and transfer it to another one

AI and ML methods can perform an exhaustive search over a huge number of potential patterns in the data and, in this way, find non-obvious, non-linear, multi-dimensional and fuzzy patterns that are hard to grasp by the human mind.

We benefit from both approaches not just by using them in parallel but by combining them into one synergetic approach.

 

 

Going beyond 'vanilla' Machine Learning at quantumrock

Going beyond 'vanilla' Machine Learning at quantumrock

High Noise-to-Signal Ratio

Financial markets are known to be very efficient, which leads to a very high noise-to-signal ratio in the financial data, which means that patterns/signals present in the data are obscured by considerable noise and, therefore, hard to detect.

Methods we apply to solve it:

No Explicit Target in the Data

The quality of an ML model is typically evaluated by comparing the model’s outcomes with so-called targets, which are present in the data. In the case of trading model development, the desired outcomes (optimal position/allocation) are not explicitly present in the data, making it impossible to use any regression model directly.

Methods we apply to solve it:

Special Objective Functions

When building trading strategies, one needs to optimize financial metrics, like Sharpe ratio or total profit with slippage, rather than metrics typically used in 'vanilla' ML, like squared or absolute error. Therefore, one cannot simply apply standard ML methods to develop trading strategies.

Methods we apply to solve it:

Special kind of time series

In finance, one works with time series that closely resemble random walks most of the time. Standard ML methods are not designed to use this information and, therefore, are not suited well for the purpose.

Methods we apply to solve it:

Dynamic Patterns

In 'vanilla' ML, patterns are usually static (e.g., for decades, cats remain the same). In contrast, financial patterns are dynamic in nature, and they can evolve, disappear, and reappear. Therefore, one has to deal with a moving target, which needs to be appropriately addressed to produce strategies that can adapt to different states of the markets and, in this way, demonstrate a stable performance.

Methods we apply to solve it:

AUTOMATION OF THE STRATEGY DEVELOPMENT PROCESS

AUTOMATION OF THE STRATEGY DEVELOPMENT PROCESS

One of the ways to achieve a stable positive performance is to use a larger number of weakly correlated and properly weighted trading strategies. To practically implement this approach, we have developed an efficient way to generate new strategies that have an added value in the context of already existing strategies.

After being fed with data, our AI Platform generates fully-fledged trading strategies by automatically performing all the steps of the model development process (features construction, model training, testing, validation and statistical testing).

View our latest whitepaper on our AI & ML approach

View our latest whitepaper on our AI & ML approach

  • What makes our approach to AI & ML different?
  • The Application of Machine Learning To Financial Markets

Our AI/ML Heads

Dr. Dr. Roman Gorbunov

Head of Machine Learning

In 2000 Roman graduated from Oles Honchar Dnipro National University in Ukraine with a master’s degree in Theoretical Physics (diploma with honors). In 2007 he finished his doctoral research in Quantum Chemistry at Goethe University in Frankfurt am Main. From 2007 to 2010, Roman conducted post-doctoral research in Theoretical Biophysics at Albert Einstein College of Medicine at Yeshiva University in New York. From 2010 to 2012, he worked at Eindhoven University of Technology on his second doctoral work in Behavioral Game Theory. Starting in 2013, Roman worked at different companies as a specialist in Data Science, Machine Learning and Mathematical Modeling. In particular, from 2013 to 2015, he worked at Blue-Yonder as a specialist in Predictive Analytics and Inventory Control based on Reinforcement Learning. From 2015 to 2017, Roman lead a team of Data Scientists developing a mathematical model of price elasticity of demand (ML on sets). From 2017 to 2018, as a Senior Research Scientist, he led a team of ML experts at Amazon to further improve the Speech Recognition model for the Alexa Virtual Assistant. Today Roman is the Head of Machine Learning at Quantumrock and is responsible for the data-driven development of trading strategies.

Nikolay Nadirashvili

Head of AI Platform

Nikolay brings more than a decade of experience at various algorithmic trading firms in Russia and applying Machine Learning at German companies (BMW, GfK).

His primary interest and expertise lies in building systematic strategies using quantitative methods and mathematical modelling of financial market dynamics. His main task at Quatumrock is the development of methodologies of automated strategy creation and validation using methods of ML and statistics and combining those methods into an AI Platform, capable of unguided strategy creation under different constraints and also using the input of domain knowledge experts as inductive bias.

Nikolay holds degrees in Economics (B.Sc.), Math (M.Sc) and Computer Science (M.Sc.) from Moscow State University and Technical University of Munich.