Market Making with informed traders

Nowadays, many types of financial contracts are traded in electronic markets. When designing algorithmic trading strategies to act in these exchanges it is important to understand the different types of trading behaviour one will encounter. An important type of market participant is the market maker, sometimes also called dealer. Her role is to facilitate trade and provide liquidity to the exchange. She does provide liquidity by posting orders on both the bid and the ask side. Typically, market makers make money by earning the spread between bid and ask prices. In addition, depending on the market venue dealers might earn a fixed/variable rebate for providing liquidity.

The optimal market making problem has been extensively studied over the years and it has been tackled with different approaches. Until recently, stochastic control is one of the widely used techniques. Lately, Machine Learning techniques have been used to find optimal market making solutions and the role of Artificial Intelligence in this field is rapidly expanding.

There are two main sources of risk that a dealer might face which have been identified in the literature. The first one is called inventory risk and arises from the fact that most of the time the dealer's inventory is not zero and it is therefore exposed to changes in the asset's valuation. The second important risk factor is called adverse selection and arises from the fact that among the crowd of market participants there are traders which have private information and try to exploit it at the dealer's expenses.

Our research project focuses on the adverse selection problem and on how to identify informed traders among market participants. Order flow is said to be toxic when it adversely selects market makers, who might not know that they are providing liquidity at a loss. Flow toxicity has been studied extensively and researchers have provided over the years two different ways of measuring it, which however have been criticised and are object of a dispute.

Our main goal is to develop a market making model where the dealer makes use of Deep Reinforcement Learning techniques to detect informed traders and adjust her quotes according to the order flow. Typical market making models assume that the dealer does not use her accumulated experience to detect patterns in participants' behaviour. Indeed, she could use her memory of the past to adjust her quotes and protect herself from exogenous information that she might not be aware of.

Our research should improve the quality of liquidity provision for both the market maker and clients which do not have any private information. Indeed, knowing that there are traders who exploit private information might help the dealer to adjust her quotes and not to trade at a loss too often. Another interesting problem that we would like to tackle is the broker perspective. A broker act in the same way as a market maker but he can decide who she wants to trade with. She could even decide arbitrarily not to trade with informed clients, and this would result in more fair quotes for other clients, who are normally trading for exogenous reasons. This however gives rise to a trade-off between losing money and finding out private information. Indeed, informed traders might be our only source of information.

This project falls within the following EPSRC areas:
1) artificial intelligence technologies
2) non-linear systems and
3) statistics and applied probability research area.
The industry partner/collaborator for this project is BNP Paribas.

Probabilistic modelling permeates the Financial services, healthcare, technology and other Service industries crucial to the UK's continuing social and economic prosperity, which are major users of stochastic algorithms for data analysis, simulation, systems design and optimisation. There is a major and growing skills shortage of experts in this area, and the success of the UK in addressing this shortage in cross-disciplinary research and industry expertise in computing, analytics and finance will directly impact the international competitiveness of UK companies and the quality of services delivered by government institutions.
By training highly skilled experts equipped to build, analyse and deploy probabilistic models, the CDT in Mathematics of Random Systems will contribute to
- sharpening the UK's research lead in this area and
- meeting the needs of industry across the technology, finance, government and healthcare sectors

MATHEMATICS, THEORETICAL PHYSICS and MATHEMATICAL BIOLOGY

The explosion of novel research areas in stochastic analysis requires the training of young researchers capable of facing the new scientific challenges and maintaining the UK's lead in this area. The partners are at the forefront of many recent developments and ideally positioned to successfully train the next generation of UK scientists for tackling these exciting challenges.
The theory of regularity structures, pioneered by Hairer (Imperial), has generated a ground-breaking approach to singular stochastic partial differential equations (SPDEs) and opened the way to solve longstanding problems in physics of random interface growth and quantum field theory, spearheaded by Hairer's group at Imperial. The theory of rough paths, initiated by TJ Lyons (Oxford), is undergoing a renewal spurred by applications in Data Science and systems control, led by the Oxford group in conjunction with Cass (Imperial). Pathwise methods and infinite dimensional methods in stochastic analysis with applications to robust modelling in finance and control have been developed by both groups.
Applications of probabilistic modelling in population genetics, mathematical ecology and precision healthcare, are active areas in which our groups have recognized expertise.

FINANCIAL SERVICES and GOVERNMENT

The large-scale computerisation of financial markets and retail finance and the advent of massive financial data sets are radically changing the landscape of financial services, requiring new profiles of experts with strong analytical and computing skills as well as familiarity with Big Data analysis and data-driven modelling, not matched by current MSc and PhD programs. Financial regulators (Bank of England, FCA, ECB) are investing in analytics and modelling to face this challenge. We will develop a novel training and research agenda adapted to these needs by leveraging the considerable expertise of our teams in quantitative modelling in finance and our extensive experience in partnerships with the financial institutions and regulators.

DATA SCIENCE:

Probabilistic algorithms, such as Stochastic gradient descent and Monte Carlo Tree Search, underlie the impressive achievements of Deep Learning methods. Stochastic control provides the theoretical framework for understanding and designing Reinforcement Learning algorithms. Deeper understanding of these algorithms can pave the way to designing improved algorithms with higher predictability and 'explainable' results, crucial for applications.
We will train experts who can blend a deeper understanding of algorithms with knowledge of the application at hand to go beyond pure data analysis and develop data-driven models and decision aid tools
There is a high demand for such expertise in technology, healthcare and finance sectors and great enthusiasm from our industry partners. Knowledge transfer will be enhanced through internships, co-funded studentships and paths to entrepreneurs