Research
MorMag believes rigorous research is the foundation of effective capital allocation. Our analysis combines macroeconomic insight, company-level fundamentals, and long-term structural thinking to identify opportunities across global markets.
Featured Research
The MorMag Quant Lab
The MorMag Quant Lab represents an ongoing effort to build research infrastructure capable of navigating complex financial markets.
The MorMag Market Scanner
The MorMag Market Scanner is positioned as the starting point in a broader analytical framework, extending beyond signal detection to function as a system for mapping opportunity across financial markets.
Inside the MorMag Quant Lab (II)
The initial development of the MorMag Quant Lab focused on building a structured research environment capable of analysing financial markets systematically.
The Limits of Prediction
Financial markets are adaptive, reflexive systems in which precise prediction is inherently constrained. Quantitative models remain valuable as tools for structuring uncertainty and informing probabilistic decision-making.
Factor Models and Market Behaviour
Factor models offer a systematic approach to understanding the drivers of market returns. By analysing recurring patterns across securities, quantitative research can provide insight into how different characteristics influence performance.
Data, Models and Reality
Quantitative methods offer powerful tools for analysing financial markets, their effectiveness depends on how they are applied.
Model Robustness in Financial Machine Learning
Robust financial models must withstand changing market conditions, data limitations, and structural shifts, ensuring signals remain reliable across varying economic environments.
Inside the MorMag Quant Lab
An overview of MorMag’s quantitative research environment, exploring how data, modelling, and systematic analysis contribute to identifying investment signals and portfolio construction insights.
From Signals to Portfolios: Translating Market Data into Investment Decisions
Quantitative signals become valuable only when translated into disciplined portfolio construction, where risk management and diversification convert insight into practical investment strategy.
Why Most Stock Prediction Models Fail
Many predictive models fail due to overfitting, unstable signals, and changing market dynamics, highlighting the importance of robustness, validation, and disciplined modelling practices.
Feature Engineering in Financial Machine Learning
Effective feature engineering transforms raw financial data into meaningful signals, enabling models to capture patterns within complex and evolving market environments.
Building a Market Intelligence Engine
Designing a systematic market intelligence framework requires integrating data pipelines, analytics, and modelling tools to uncover patterns across global financial markets.