arXiv subjects

Anisoara Calinescu

Publications and source records attributed to Anisoara Calinescu.

26 records · Page 2Linked to original sources

arXiv2023

JAX-LOB: A GPU-Accelerated limit order book simulator to unlock large scale reinforcement learning for trading

Financial exchanges across the world use limit order books (LOBs) to process orders and match trades. For research purposes it is important to have large scale efficient simulators of LOB dynamics. LOB simulators have previously been implemented in the context of agent-based models (ABMs), reinforcement learning (RL) environments, and generative models, processing order flows from historical data sets and hand-crafted agents alike. For many applications, there is a requirement for processing multiple books, either for the calibration of ABMs or for the training of RL agents. We showcase the first GPU-enabled LOB simulator designed to process thousands of books in parallel, with a notably reduced per-message processing time. The implementation of our simulator - JAX-LOB - is based on design choices that aim to best exploit the powers of JAX without compromising on the realism of LOB-related mechanisms. We integrate JAX-LOB with other JAX packages, to provide an example of how one may address an optimal execution problem with reinforcement learning, and to share some preliminary results from end-to-end RL training on GPUs.

q-fin.TR↗

arXiv2023

Generative AI for End-to-End Limit Order Book Modelling: A Token-Level Autoregressive Generative Model of Message Flow Using a Deep State Space Network

Developing a generative model of realistic order flow in financial markets is a challenging open problem, with numerous applications for market participants. Addressing this, we propose the first end-to-end autoregressive generative model that generates tokenized limit order book (LOB) messages. These messages are interpreted by a Jax-LOB simulator, which updates the LOB state. To handle long sequences efficiently, the model employs simplified structured state-space layers to process sequences of order book states and tokenized messages. Using LOBSTER data of NASDAQ equity LOBs, we develop a custom tokenizer for message data, converting groups of successive digits to tokens, similar to tokenization in large language models. Out-of-sample results show promising performance in approximating the data distribution, as evidenced by low model perplexity. Furthermore, the mid-price returns calculated from the generated order flow exhibit a significant correlation with the data, indicating impressive conditional forecast performance. Due to the granularity of generated data, and the accuracy of the model, it offers new application areas for future work beyond forecasting, e.g. acting as a world model in high-frequency financial reinforcement learning applications. Overall, our results invite the use and extension of the model in the direction of autoregressive large financial models for the generation of high-frequency financial data and we commit to open-sourcing our code to facilitate future research.

q-fin.TR↗

arXiv2023

Some challenges of calibrating differentiable agent-based models

Agent-based models (ABMs) are a promising approach to modelling and reasoning about complex systems, yet their application in practice is impeded by their complexity, discrete nature, and the difficulty of performing parameter inference and optimisation tasks. This in turn has sparked interest in the construction of differentiable ABMs as a strategy for combatting these difficulties, yet a number of challenges remain. In this paper, we discuss and present experiments that highlight some of these challenges, along with potential solutions.

cs.MA↗

arXiv2023

Bayesian calibration of differentiable agent-based models

Agent-based modelling (ABMing) is a powerful and intuitive approach to modelling complex systems; however, the intractability of ABMs' likelihood functions and the non-differentiability of the mathematical operations comprising these models present a challenge to their use in the real world. These difficulties have in turn generated research on approximate Bayesian inference methods for ABMs and on constructing differentiable approximations to arbitrary ABMs, but little work has been directed towards designing approximate Bayesian inference techniques for the specific case of differentiable ABMs. In this work, we aim to address this gap and discuss how generalised variational inference procedures may be employed to provide misspecification-robust Bayesian parameter inferences for differentiable ABMs. We demonstrate with experiments on a differentiable ABM of the COVID-19 pandemic that our approach can result in accurate inferences, and discuss avenues for future work.

cs.MA↗

arXiv2021

Supply Chain Digital Twin Framework Design: An Approach of Supply Chain Operations Reference Model and System of Systems

Digital twin technology has been regarded as a beneficial approach in supply chain development. Different from traditional digital twin (temporal dynamic), supply chain digital twin is a spatio-temporal dynamic system. This paper explains what is 'twined' in supply chain digital twin and how to 'twin' them to handle the spatio-temporal dynamic issue. A supply chain digital twin framework is developed based on the theories of system of systems and supply chain operations reference model. This framework is universal and can be applied in various types of supply chain systems. We firstly decompose the supply chain system into unified standard blocks preparing for the adoption of digital twin. Next, the idea of supply chain operations reference model is adopted to digitise basic supply chain activities within each block and explain how to use existing information system. Then, individual sub-digital twin is established for each member in supply chain system. After that, we apply the concept of system of systems to integrate and coordinate sub-digital twin into supply chain digital twin from the views of supply chain business integration and information system integration. At last, one simple supply chain system is applied to illustrate the application of the proposed model.

eess.SY↗

arXiv2021

How Market Ecology Explains Market Malfunction

Standard approaches to the theory of financial markets are based on equilibrium and efficiency. Here we develop an alternative based on concepts and methods developed by biologists, in which the wealth invested in a financial strategy is like the abundance of a species. We study a toy model of a market consisting of value investors, trend followers and noise traders. We show that the average returns of strategies are strongly density dependent, i.e. they depend on the wealth invested in each strategy at any given time. In the absence of noise the market would slowly evolve toward an efficient equilibrium, but the statistical uncertainty in profitability (which is adjusted to match real markets) makes this noisy and uncertain. Even in the long term, the market spends extended periods of time away from perfect efficiency. We show how core concepts from ecology, such as the community matrix and food webs, give insight into market behavior. The wealth dynamics of the market ecology explain how market inefficiencies spontaneously occur and gives insight into the origins of excess price volatility and deviations of prices from fundamental values.

q-fin.GN↗

arXiv2020

Digital Twins: State of the Art Theory and Practice, Challenges, and Open Research Questions

Digital Twin was introduced over a decade ago, as an innovative all-encompassing tool, with perceived benefits including real-time monitoring, simulation and forecasting. However, the theoretical framework and practical implementations of digital twins (DT) are still far from this vision. Although successful implementations exist, sufficient implementation details are not publicly available, therefore it is difficult to assess their effectiveness, draw comparisons and jointly advance the DT methodology. This work explores the various DT features and current approaches, the shortcomings and reasons behind the delay in the implementation and adoption of digital twin. Advancements in machine learning, internet of things and big data have contributed hugely to the improvements in DT with regards to its real-time monitoring and forecasting properties. Despite this progress and individual company-based efforts, certain research gaps exist in the field, which have caused delay in the widespread adoption of this concept. We reviewed relevant works and identified that the major reasons for this delay are the lack of a universal reference framework, domain dependence, security concerns of shared data, reliance of digital twin on other technologies, and lack of quantitative metrics. We define the necessary components of a digital twin required for a universal reference framework, which also validate its uniqueness as a concept compared to similar concepts like simulation, autonomous systems, etc. This work further assesses the digital twin applications in different domains and the current state of machine learning and big data in it. It thus answers and identifies novel research questions, both of which will help to better understand and advance the theory and practice of digital twins.

cs.LG↗

arXiv2018

Understanding Flash Crash Contagion and Systemic Risk: A Micro-Macro Agent-Based Approach

The purpose of this paper is to advance the understanding of the conditions that give rise to flash crash contagion, particularly with respect to overlapping asset portfolio crowding. To this end, we designed, implemented, and assessed a hybrid micro-macro agent-based model, where price impact arises endogenously through the limit order placement activity of algorithmic traders. Our novel hybrid microscopic and macroscopic model allows us to quantify systemic risk not just in terms of system stability, but also in terms of the speed of financial distress propagation over intraday timescales. We find that systemic risk is strongly dependent on the behaviour of algorithmic traders, on leverage management practices, and on network topology. Our results demonstrate that, for high-crowding regimes, contagion speed is a non-monotone function of portfolio diversification. We also find the surprising result that, in certain circumstances, increased portfolio crowding is beneficial to systemic stability. We are not aware of previous studies that have exhibited this phenomenon, and our results establish the importance of considering non-uniform asset allocations in future studies. Finally, we characterise the time window available for regulatory interventions during the propagation of flash crash distress, with results suggesting ex ante precautions may have higher efficacy than ex post reactions.

q-fin.TR↗