Disclaimer

The information contained is not intended for publication, use or distribution to or by any person from any other country. In particular, this information is not intended for distribution in the United States of America (USA), for citizens of the USA or for persons resident or domiciled in the USA or persons acting on their behalf. The content provided is for information purposes only. In particular, it does not constitute an offer to sell, buy or subscribe to securities or other instruments. Insofar as persons resident or domiciled abroad access the information contained on the website, the operator of the website does not give any assurance or guarantee that the information contained complies with the provisions applicable in the country concerned.

All information on this website is intended exclusively for persons domiciled or habitually resident in Germany. Furthermore, I confirm that I am a professional investor within the meaning of Section 67 II of the German Securities Trading Act (WpHG). I am aware that I enjoy a reduced level of protection compared to a private client with regard to financial services.

This website uses cookies to improve the user experience. By using this website, you agree to the use of cookies by our website. I confirm that I meet the above requirements with regard to the investor group and have read, understood and accepted the information regarding the use and distribution restrictions.

Our AI-Driven Approach

Our distinct market philosophy and deep AI expertise empower us to craft and deliver superior, customized investment solutions.

Animation

Our Mission

We are pioneers for a new generation of capital market models based on Artificial Intelligence. Empowering professional and private investors to make informed investment decisions - enabling them to create sustainable and greater value - that's what we stand for.

Our Competencies

Building on the transformative power of Machine Learning, we translate theoretical advantages into practical, value-adding AI competencies.

AI-Powered Stock Selection

Ultramarin leverages ML to build holistic valuation models for stock selection. These models integrate a vast array of economically sound features from diverse data sets and different valuation schools, including fundamental analysis and behavioral finance insights. This comprehensive approach allows our ML architecture to utilize these features to predict expected returns and associated uncertainty. It captures complex, often non-linear relationships that traditional methods miss, resulting in superior prediction quality compared to traditional econometric models and thus enabling more informed investment decisions.

Tactical Equity Allocation

Our proprietary "Fast-and-Slow" approach provides informed tactical equity allocation based on AI. Inspired by Daniel Kahneman's work on human cognition, this holistic approach is based on an ML model trained to predict the impact of both intuitive (System 1) and rational (System 2) market behaviors on risk premiums. It acts as a robust early warning system in today's complex, fast-moving markets. Unlike classical econometric models that struggle with data heterogeneity, our ML methods deliver superior prediction quality, supporting sharper and more effective allocation choices.

Our View

Machine Learning delivers significant value-add for informed investment decisions, by transcending human biases and traditional quant limits in efficiently inefficient markets.

Market Dynamics & Alpha

Our understanding of capital markets aligns with the concept of "efficiently inefficient markets" (Pedersen, 2015). This theory posits that while intense competition among professional investors makes markets nearly efficient, enough inefficiencies persist to reward skilled active managers for their costs and risks. Within such markets, alpha can be generated through two primary approaches: informed decisions by highly experienced human experts, or by models and quantitative methods run by machines.

Model Superiority & Quant's Evolution

Models consistently surpass human investment decisions due to inherent noise and biases in human judgment. As Nobel laureate Daniel Kahneman points out, models are free from this "noise" and are thus consistently more accurate. Though fundamental since the 1980s for various analytical and optimization tasks, traditional quantitative models face limitations in high-dimensional markets: they struggle with a large number of variables (prone to overfitting), primarily map complex relationships linearly, and are slow to adapt to structural market breaks.

The ML Advantage

This is where Machine Learning (ML) provides a distinct advantage. Unlike traditional linear models that make strong assumptions about data, flexible ML techniques allow us to learn complex relationships without imposing restrictive parametric assumptions (Hastie et al., "The Elements of Statistical Learning", 2009). This directly mitigates the limitations of traditional models. ML enables us to analyze more influencing factors simultaneously, better understand complex non-linear relationships, and significantly enhance prediction quality through holistic modeling and adaptive approaches.

Contact Us

We look forward to hearing from you