Price of 5-year credit default swap (coupon=100) at the close of the market on , at 5:00 PM GMT (source: DataGrapple).
One Instrument: The CDS
The credit default swap (“CDS”) is a financial instrument enabling the transfer of an issuer’s credit risk between two investors. The CDS provides investors with a liquid tool for hedging or investing. The price of a CDS is the market barometer for the risk of a borrower.
One Process: Arbitrage
Arbitrage is an investment technique that combines purchases and sales of financial instruments having offsetting risks. The net return on the portfolios thus combined is the arbitrage profit. The performance of arbitrage portfolios is not governed by the performance of the financial markets. Arbitrages are investment processes that use leverage – such investments are restricted to professional investors.
One Team: HC
Hellebore Capital (HC) is a management company specializing in credit derivatives arbitrage. Its technology gives HC the ability to operate in all the credit derivatives markets of Asia, Europe and North America. If you would like to learn more about HC and its products, you can create an account online. HC is regulated by the French Authorité des marchés financiers (“AMF”).
ANALYST DATA / IT FRONT OFFICE
Hellebore Capital, Paris in association with its FinTech sister company, Hellebore Technologies, Paris has developed a front-to-back real-time solutions platform to invest in over-the-counter credit derivatives markets.
Within this context, Hellebore rethinks continuously the
way it sources, validates and distributes data and this, in turn, design drives and adoption of new architectures covering all aspects of data handling including sourcing, cleaning,
transformation, enrichment, transmission and storage.
The Analyst DATA / IT Front Office position is at the critical centre of our business and our dynamic, developmental environment requires innovative strategic thinking and immediate, real-time solutions.
Analyst DATA / IT Front Office will be in charge of developing on-the-fly solutions, leveraging the existing Hellebore open architecture. They will be expected to leverage
the numerous internal Python's libraries, the company's large-scale computing capacity and various web portals.
Analyst DATA / IT Front Office will also be closely related to a new Django project for data dissemination.
WHO WE ARE LOOKING FOR. The Analyst DATA / IT Front Office will be responsible for developing tools used to streamline investment decisions, risk analysis or operational processes
directly interacting with front office traders and leveraging our technology partners. Hellebore is looking for innovators and problem-solvers, providing market risk management solutions,
big data and more; the successful candidate will oversee the operation of its platforms and support the continuing automation of processes.
Hellebore focuses on automation and 'tooling' both to eliminate unnecessary manual effort and to enhance
- Owning the relationship between the portfolio managers and the technology partners
- Developing specialist knowledge in systems, sharing knowledge with team members and partners
- Managing projects through completion, adhering to project-management best practices
- You have knowledge of Trading or Risk Functions - or can adapt your existing experience to the financial markets.
- You have experienced the demanding nature of delivering real time solutions.
- You are experienced in SQL and have a strong understanding of how relational databases work.
- You know Python to an advanced level to automate processes or have a development background
Hellebore Capital is a hedge fund specializing in Credit Default Swaps arbitrage since 2013. The Company has steadily increased its assets under management based on this highly focused investment strategy. Combining new technologies with its over-the-counter dealer relationships, the Company can invest in the global credit markets to deliver specific opportunities for alpha for its investors. The Company is now working on the launch of a new investment vehicle, leveraging past years’ research efforts. Hellebore Capital’s R&D team combines multiple aspects of machine learning technologies to monitor the CDS markets, to detect investment opportunities and to assess risks.
The Quantitative Research position will reinforce Hellebore Capital agile and challenging research team.
The Quantitative Research position will be in charge of digging into statistical / machine learning ideas in a constant dialogue with portfolio managers.
WHO WE ARE LOOKING FOR.
The Quantitative Research Scientist will be responsible of several research projects. He / She must be able to present innovative and challenging ideas as well as to implement them.
He / She must be able to popularize his work to the whole team.
- Developing and improving Hellebore Capital statistical / Machine Learning models over OTC transactions and CDS time series.
- Updating Hellebore research standards, sharing knowledge with team members and partners.
- Being a creative force : translating research efforts into trading ideas.
- Contributing to Hellebore Capital's influence & monitoring technology intelligence by publishing research articles and attending top conferences.
- You have a Master degree or PhD in Finance / Stochastic Calculus / Statistics / Data Science.
- You fit and enjoy both aspects of R & D : Research (Ability to go through state-of the-art, suggest and test innovative ideas) and Development (Ability to present research contributions and implement them into Hellebore systems, to build visualization tools) .
- You have Python programming skills.
- You are resourceful and present a curious mindset.
- Experiences in Hawkes Processes is a plus.
This position is also opened to students looking for a 6 month internships (end-of-studies internship, gap-year internship etc).
Research and Development
About Hellebore Capital's R&D
Hellebore Capital's R&D team focuses on credit default swap (CDS) time series modelling, both to define quantitative investment strategies or to design new risk management frameworks.
The team has developed an expertise in clustering algorithms, a set of machine-learning techniques which clusters assets demonstrating similar behaviours. These techniques are providing resilient results despite noise and jumps characteristics of CDS time series. More recently, some of the research efforts have concentrated on asynchronous time series description and prediction. Amongst other topics, Natural Language Processing techniques have been explored as well, hand in hand with Hellebore Technologies, a sister company.
The team publishes some of its results and participates in various conferences. We think this is good practice to constantly challenge our ideas.
By hosting interns or monitoring projects with PhD students, Hellebore Capital has established partnerships with universities amongst the best in Europe : the Ecole Polytechnique (France), Imperial College (London), etc. Groups of students from ENSAE (France) has also been supervised on Data Science projects.
We are always looking for resourceful and motivated people, do not hesitate to apply to any of our research open positions. If nothing fits your prospects & skills, we do encourage spontaneous applications through Hellebore HR.
Selection of published articles
Toward a generic representation of random variables for machine learning
This paper introduces a new representation of time series and an associated metric for clustering time series in homogeneous sets. The representation is applied to CDS time series. It essentially refines clusters of correlated assets by taking into account the marginal distribution of their returns. The method provides stable and reliable clusters.
A proposal of a methodological framework with experimental guidelines to investigate clustering stability on financial time series
This paper proposes a methodology to assess the robustness of clusters. Besides, it also aims to understand asset clustering invariants and to answer questions such as: "Are clusters the same
using daily/weekly/monthly returns, using different maturities in the CDS term structure, both during bear and bull periods"?
Clustering Financial Time Series: How Long is Enough?
This paper also tackles the question of clustering stability, but from more of a theoretical point of view. We first show that the clustering methodology can be consistent.
This means that the clusters obtained from the algorithm converge to the correct clusters. This also means that there is a minimum value of the time sample T (in practice, a minimum number of returns observed in the historical time series) required so that the clusters obtained are correct. We show that this minimum value T is strongly dependent of the clustering methodology. The challenge for us is then to find the clustering methodology which yields the smallest possible T. The smaller the T, the more relevant the applications of clustering financial time series can be.
Optimal Copula Transport for Clustering Multivariate Time Series
This paper contains several ideas and opens several research directions for us. We focus on (i) Understanding dependence between objects described by several time series; (ii) Defining new dependence coefficients which can robustly target specific dependence patterns; and (iii) Studying various geometries for copulas. We also explore issues such as the distance between these objects, empirical 'ergodicity' and the rate of convergence of the clustering algorithms when the objects are described by several time series.
A Review of Two Decades of Correlations, Hierarchies, Networks and Clustering in Financial Markets
This paper is an ongoing review on the state of the art of clustering financial time series and the study of correlation and other interaction networks. It aims at gathering in one place the relevant material that can help the researcher in the field to have a bigger picture, the quantitative researcher to play with this alternative modeling of the financial time series, and the decision maker to leverage the insights obtained from these methods.
Past and Foreseen Conferences
We will give and gave talks at these machine learning conferences:
- 19-21 September 2018,
Analyzing credit indices time series: How random are trades arrival times?,
- 10-15 July 2018,
Autoregressive Convolutional Neural Networks for Asynchronous Time Series,
- 10-15 July 2017,
Putting Self-Supervised Token Embedding on the Tables,
IEEE ICMLA 2017,
- 5-10 December 2016,
Exploring and measuring non-linear correlations: Copulas, Lightspeed Transportation and Clustering,
NIPS Time Series Workshop 2016,
9-11 December 2016,
Empirical convergence rates of dependence-based clustering methods illustrated with financial time series,
9th International Conference on Computational and Methodological Statistics - CMStatistics 2016,
9-15 July 2016,
Clustering Financial Time Series: How Long is Enough?,
25th International Joint Conference on Artificial Intelligence - IJCAI 2016,
New York Hilton Midtown Hotel, New York City, USA.
26-29 June 2016,
Optimal transport vs. Fisher-Rao distance between copulas for clustering multivariate time series,
IEEE Workshop on Statistical Signal Processing - SSP 2016,
Palma de Mallorca, Spain.
19-24 June 2016,
Which Geometry for Clustering Copulas?,
33rd International Conference on Machine Learning - ICML 2016,
workshop Gimli: Geometry in Machine Learning,
New York City, NY, USA.
20-25 March 2016,
Optimal Copula Transport for Clustering Multivariate Time Series,
41st IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP 2016,
Shanghai International Convention Center, Shanghai, China.
9-11 December 2015,
A proposal of a methodological framework with experimental guidelines to investigate clustering stability on financial time series,
14th International Conference on Machine Learning and Applications - IEEE ICMLA 2015,
Miami, Florida, USA.
28-30 October 2015,
Clustering Random Walk Time Series,
2nd conference on Geometric Science of Information - GSI 2015,
Ecole Polytechnique, Palaiseau, France.
21-25 September 2015,
On clustering financial time series: a need for distances between dependent random variables,
Computational information geometry for image and signal processing - CIGISP 2015,
International Centre for Mathematical Sciences, Edinburgh, UK.
8-11 September 2015,
Comment partitionner automatiquement des marches aléatoires ? Avec application à la finance quantitative,
Ecole Normale Supérieure de Lyon, Lyon, France.
6-11 July 2015,
On Clustering Financial Time Series
32nd International Conference on Machine Learning - ICML 2015,
We also participate to various AI / Machine Learning / Big Data / FinTech meetings in Paris and London:
We propose internships on the following topics:
- High Performance Computing for Machine Learning
- Bayesian inference of market variables
Unsolicited applications from graduate students in math, physics, machine learning, financial engineering with strong computational skills
are most welcomed.