Market ecology modeling

The theory of market ecology (Farmer, 2002; LeBaron, 2002; Musciotto et al., 2018; Lo, 2019; Levin & Lo, 2021; Scholl et al., 2021) borrows concepts from ecology and biology to study financial markets. Viewing them as ecosystems populated with species of various types (institutions, retail investors, funds, securities) allows one to develop a complementary perspective. Notably, trading strategies and fund investment styles are analogous to biological species: they exploit market inefficiencies and compete for survival or profit. (Scholl et al., 2021) has highlighted the nature of interactions between common trading strategies and the strong density dependence of their returns.

In this project, we consider the world of mutual funds, composed of many investment styles: Value, Growth, Blend, Momentum, Income and Dividend, to only cite a few main styles. In the past decade, macroeconomic conditions have been favorable to the Growth style, but with the latest rises in interest rate and stock market decline, Value makes a comeback. Styles' financial performance is affected by external economic factors, but their endogenous interaction is largely unknown. Previous market ecology research has shown that the composition of the market between different strategies had a substantial impact on the returns of each strategy and that this composition impacted market states such as mispricing and volatility. We are thus examining whether an artificial stock market populated with those various investment styles can generate such endogenous interactions.

To tackle this research question, we have been for the first two years of the PhD developing a new agent-based simulation model that models individual funds of different styles interacting endogenously in a stylised financial market. We emphasize empirical calibration of the simulation. In particular, we are working on seeding the fund population in adequation with real market composition by looking at regulatory filings. We model in great detail the dynamics of fund net flows, as investors can invest or redeem their fund shares depending on the fund performance track record. We are also working on populating the financial environment in our model with stocks of realistic companies at various growth stages.

Many applications are open from this research. Policy makers and regulators can obtain a novel source of information about the market dynamics. Market participants may gain an edge to decide the positioning of their investment and better anticipate future market states. The agent-based simulation offers a new, complex framework for trading strategy search with machine learning and evolutionary computation methods: reinforcement learning, genetic programming, genetic algorithms, program synthesis, deep neural networks. We have recently started to include interest rates in the model to understand how changes in interest rates, as seen recently, change the composition of the market. In addition, policy interventions such as quantitative easing and tightening can easily be added to the model to model the ecology impact of those measures.

This project has received the support of Fidelity Investments and an article about this research submitted to the ICML22 conference has received a Best Paper award.

This project falls within the following EPSRC research areas: artificial intelligence technologies, digital economy, biological informatics, Complexity science, Operational Research

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