A new era for systematic investing.

Walnut Investments is a quantitative investment management company applying artificial intelligence to absolute return strategies. We combine advanced machine learning techniques with financial expertise to generate profitable, self-learning trading systems.

What we do.

Research Image


A majority of our time is spent on research. It is a demanding but rewarding process. It means collaborating and sharing ideas, but also arguing about them. We use cutting-edge proprietary research tools and computing libraries; and seek to build beyond them.

Develop Image


Technology is our passion and quickly building reliable systems is one of our principles. We are a development company that embraces agile practices. We incorporate Scrum methodology, Test Driven Development, and Continuous Integration into our daily lives.

Create Image


Our mission is to rethink traditional investment management. Building something new requires an environment that positively nurtures creativity. Cross-knowledge, scientific expertise, and solid modular foundations compose our elements of innovation.

Working and thriving.

Our systems result from an intense collaboration among a diverse, highly-specialised group of scientists and researchers from the fields of artificial intelligence, mathematics, quantitative trading, and computer science.


Adrien Fischman

Machine learning researcher, Adrien holds master's degrees in machine learning from Université Grenoble Alpes and in mathematics and computer science from ENSIMAG.


Adrien Pain

Quant researcher, Adrien was formerly quant at OptimInvest as well as Overlay Asset Management (BNP Paribas). He was previously R&D engineer at Eurodecision. Adrien holds master's degrees in artificial intelligence from EPITA and in mathematics from Université Paris Dauphine.


Andrew Mittleider

Software engineer, Andrew was previously at Microsoft. He holds a master's degree in computer science from University of Nebraska-Lincoln.


Basile Mayeur

Overseeing Walnut's research efforts, Basile was previously PhD candidate in deep reinforcement learning at Université Paris-Sud (CNRS-INRIA). He holds master's degrees in machine learning from Université Paris-Sud and in mathematics and computer science from ENSIMAG.


Benjamin Le Maitre

Business associate, Benjamin is specialised in financial engineering and alternative investments. He holds a master's degree from ESSCA and the Chartered Alternative Investment Analyst (CAIA) designation.


Carl Levasseur

Software engineer, Carl holds a master's degree in data mining and analytics for decision making from UTC as well as a BSc in computer science from Université des Sciences et Technologies de Lille.


Colombe De Milly

Machine learning researcher, Colombe was previously data scientist at Criteo. She holds master's degrees in engineering from Centrale-Supélec and in mathematical modelling and scientific computing from the University of Oxford.


Damien Mourot

Responsible for software engineering, Damien was previously an R&D engineer at Misys Sophis (now Finastra). He holds a master's degree in applied mathematics and computer science from ENSIMAG.


Estelle Campos

In charge of people operations, Estelle was previously at Leroy Merlin, Jumia, and Deezer. She holds a master's degree in international human resources management from ESC Rennes.


Guillaume Vidal

CEO at Walnut, Guillaume was previously a private equity professional at Keyhaven Capital Partners in London. He holds master's degrees in computer science from Imperial College London, and in finance from the London School of Economics.


Kevin Lourd

Running operations at Walnut, Kevin was previously associate consultant with Bain & Company. He holds master's degrees in business administration and strategy from ESSEC Business School, and in applied mathematics and computer science from ENSIMAG .


Laurent Nguyen

Software engineer, Laurent was previously a contractor to SGCIB, Natixis and Engie Global Markets. He holds master's degrees in applied mathematics and computer science from ENSIMAG and in quantitative finance from IAE Grenoble.


Lionel Limery

Trading strategies specialist, Lionel was previously project manager at AXA Investment Managers, futures trader at IDT (Futex) and IT quant at Overlay Asset Management (BNP Paribas). He holds an MBA in financial markets and portfolio management from ESLSCA as well as an engineering degree from ESIEE.


Martin Mihelich

Mathematics researcher at Walnut and lecturer in mathematics (classes préparatoires), Martin is agrégé in mathematics. He also holds a PhD in mathematics and theoretical physics as well as a master's degree in mathematics, both from Ecole Normale Supérieure (Ulm).


Michaël Blot

Machine learning researcher at Walnut, Michaël holds a PhD in deep learning at UPMC. Previously quantitative researcher at BNP Paribas, he holds master's degrees in mathematical logic from Université Paris Diderot, in quantitative finance from IAE Grenoble, and mathematics and computer science from ENSIMAG.


Robin Monnier

Machine learning researcher, Robin holds master's degrees in data science from Ecole Polytechnique and mathematics and computer science from Ecole des Ponts ParisTech.


Tristan Marechaux

Software engineer, Tristan holds a master's degree in mathematics and computer science from ENSIMAG.


Yan Shu

Mathematics researcher, Yan holds a PhD in mathematics from Paris-Nanterre and a master's degree in mathematics from Ecole Normale Supérieure (Lyon).


Sébastien Gaspar

Software Engineer at Walnut, Sébastien was previously Software Engineer at Criteo, Natixis, Invivoo and Crédit Agricole CIB. He holds a master's degree in computer science from ENSEA.


Maxime Gauthier

Software Engineer at Walnut, Maxime was previously Software Engineer at Société Générale and Natixis. He holds a master's degree in mathematics and computer science from ENSIMAG.


Question the obvious

Express your true self

Dare to be wrong

Take ownership

Question the obvious

Walnut has developed a work environment where opposing views are promoted, and where the best idea should always win, no matter how crazy it may first seem. Even newcomers are expected to challenge both senior researchers and common knowledge.

Express your true self

We want Walnut to be a place where we can share life experiences. We encourage you to express your true self without any corporate mask through bootcamps, offsites, and travelling to scientific conferences. Creative research needs more than mathematics!

Dare to be wrong

Your ideas will be challenged and you will often be wrong; it is part of the job and the only way to find out the hard truths. At Walnut, you will be applauded for expressing your views, even if inaccurate. You will experience how being 'smartly wrong' often brings a better solution.

Take ownership

We are a team-owned business and all members hold equity. Major decisions about research, software, and our business are discussed collectively and taken transparently. We think there is no point in succeeding alone.

How we build our technology.

We believe that machine intelligence within investment will be dominant and is unavoidable. This belief underpins our work using core data-driven discoveries and statistical decision making. Integral to this work is our use of robust data analysis, data-powered decision making, intense collaboration, and the protection of creativity.

Machine learning

We use machine learning for fast, accurate, and continuous learning of vast amounts of data while avoiding rigid rules. Key for finance, it also provides a powerful formalism to measure and control statistical robustness and overfitting.

Computer science

We develop using diligent practices and the most advanced technologies. Open source libraries are carefully leveraged to reduce time to market. Our approach allows us to preserve the maintainability and resilience of our trading systems.


Quantitative investing means operating at the opposite of randomness – it bans gut-feels and discretionary decision making. It seeks to maximise statistical significance by rigorously applying mathematics rooted in market rationale, consistently.


Diversification is only one measure to reduce risk. In times of crisis everything tends to correlate. We believe risk management must be achieved with careful designs, robust market signals, statistical significance, protected positions, and controlled levels of exposure.


“Walnut joins a small group of hedge funds that use artificial intelligence to trade.”

Becky Pritchard, 31 January 2017.

“Walnut was designed from the beginning to work on AI.“

Spencer Platt, 26 February 2017.

“The underlying algo itself understands that the market has changed and gives us higher or lower confidence on its signal.“

Guillaume Vidal, Dataconomy interview, 5 April 2017.

Walnut Investments SASU is a French portfolio management company regulated by the Autorité des Marchés Financiers (AMF) under number GP-18000021 with a share capital of 1 010 000€.

The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by Walnut.

In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Walnut nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security 
Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or 
other investor, contact your financial advisor or other fiduciary unrelated to Walnut about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Walnut makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances. As Walnut Algorithms is fully dedicated to this sole project, its team as been presented in this website along with the Walnut Investments team.