Quantitative Researcher, MRM Research

Nico Rosti

I have been working for +17 years as a quantitative researcher, offering my investment research insights to investors through two private companies I have founded (Retracement Levels Ltd. and QUANTRADING AG); more recently I worked as a Portfolio Manager at Capital Theory Investment Management, LLC, a CTA based in Austin, Texas (USA), where I developed and ran automated algorithmic trading strategies for the US Futures and Options markets. 

My research work is focused on the statistical study of the "persistence of trends" and "mean reversion" effects in global Equities, Futures, Indexes, Bonds and FX Spot markets. I have created an original proprietary process (called the "Market Reversal Matrix" or "MRM") that makes extensive use of probabilistic Bayesian models to predict short-term (1 day to few weeks) trend reversals.

I do not use any AI/machine learning processes in my work: all models and algorithms are built and supervised by humans. This approach is very labour-intensive but produces forecasts that have a clearly understandable/explainable rationale (no black-boxes).

Quantitative Researcher

EQD | Decoding Last Week's HSI Retreat: What Lies Ahead?

EQD | The Hang Seng Index May Go Higher 2

EQD | Introducing the Market Reversal Matrix (MRM): Predict Trend Reversal with Bayesian Models

MRM Research

Quantitative Research

Quantitative Analysis

<ul>
<li>Numerous studies conducted over the past few decades have researched the “month of the year effect” in global stock markets, and tend to agree that some effects do exist.</li>
<li>Most studies however concur that seasonality, on its own, is a weak predictor of performance. We call these studies “Naïve Seasonality Analysis”, for reasons that we will explain here.</li>
<li>Based on the above premise, in this Smartkarma Original we are going to propose a methodology to improve seasonality research, to identify <em>when</em> specific months can deliver the best returns.</li>
</ul>


Numerous studies conducted over the past few decades have researched the “month of the year effect” in global stock markets, and tend to agree that some effects do exist.
Most studies however concur that seasonality, on its own, is a weak predictor of performance. We call these studies “Naïve Seasonality Analysis”, for reasons that we will explain here.
Based on the above premise, in this Smartkarma Original we are going to propose a methodology to improve seasonality research, to identify when specific months can deliver the best returns.


Influence of Monthly Time Patterns on Seasonal Effects in Asian Stock Markets: NKY and HSI