Get real

Vyetrenko, Svitlana; Byrd, David R.; Petosa, Nick; Mahfouz, Mahmoud; Dervovic, Danial; Veloso, Manuela; Balch, Tucker

doi:10.1145/3383455.3422561

Cited by 24 publications

(12 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These models are described in subsection 3.1. Most calibration methods for market simulators use a collection of summary features known in economics and finance as stylised facts [36,41,42]. The stylised facts represent commonly observed features generated by market exchanges.…”

Section: Methodsmentioning

confidence: 99%

Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks

Stillman,

Baggott,

Lyon

et al. 2023

4th ACM International Conference on AI in Finance

View full text Add to dashboard Cite

The ability to construct a realistic simulator of financial exchanges, including reproducing the dynamics of the limit order book, can give insight into many counterfactual scenarios, such as a flash crash, a margin call, or changes in macroeconomic outlook. In recent years, agent-based models have been developed that reproduce many features of an exchange, as summarised by a set of stylised facts and statistics. However, the ability to calibrate simulators to a specific period of trading remains an open challenge. In this work, we develop a novel approach to the calibration of market simulators by leveraging recent advances in deep learning, specifically using neural density estimators and embedding networks. We demonstrate that our approach is able to correctly identify high probability parameter sets, both when applied to synthetic and historical data, and without reliance on manually selected or weighted ensembles of stylised facts.

show abstract

Section: Methodsmentioning

confidence: 99%

Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks

Stillman,

Baggott,

Lyon

et al. 2023

4th ACM International Conference on AI in Finance

View full text Add to dashboard Cite

show abstract

“…The Thirty-Eighth AAAI Conference on Artificial Intelligence bined the agent-based model with stochastic models (Shi and Cartlidge 2023). While agent-based models offer insights by simulating individual agent behaviors, they rely heavily on behavior models of agents and empirical market models, which sheds some doubts on the plausibility of using this method to simulate complex market (Gould et al 2013;Preis et al 2007;Vyetrenko et al 2020). While the price feature is an important data source, especially in fundamental and technical analysis as illustrated by (Petrusheva and Jordanoski 2016;Dechow et al 2001;Gite et al 2021;Miao 2014), its simulation is also essential.…”

Section: Background and Related Workmentioning

confidence: 99%

Market-GAN: Adding Control to Financial Market Data Generation with Semantic Context

Xia,

Sun,

Wang

et al. 2024

AAAI

View full text Add to dashboard Cite

Financial simulators play an important role in enhancing forecasting accuracy, managing risks, and fostering strategic financial decision-making. Despite the development of financial market simulation methodologies, existing frameworks often struggle with adapting to specialized simulation context. We pinpoint the challenges as i) current financial datasets do not contain context labels; ii) current techniques are not designed to generate financial data with context as control, which demands greater precision compared to other modalities; iii) the inherent difficulties in generating context-aligned, high-fidelity data given the non-stationary, noisy nature of financial data. To address these challenges, our contributions are: i) we proposed the Contextual Market Dataset with market dynamics, stock ticker, and history state as context, leveraging a market dynamics modeling method that combines linear regression and clustering to extract market dynamics; ii) we present Market-GAN, a novel architecture incorporating a Generative Adversarial Networks (GAN) for the controllable generation with context, an autoencoder for learning low-dimension features, and supervisors for knowledge transfer; iii) we introduce a two-stage training scheme to ensure that Market-GAN captures the intrinsic market distribution with multiple objectives. In the pertaining stage, with the use of the autoencoder and supervisors, we prepare the generator with a better initialization for the adversarial training stage. We propose a set of holistic evaluation metrics that consider alignment, fidelity, data usability on downstream tasks, and market facts. We evaluate Market-GAN with the Dow Jones Industrial Average data from 2000 to 2023 and showcase superior performance in comparison to 4 state-of-the-art time-series generative models.

show abstract

“…For example, while games such as Go or StarCraft can be repeated infinitely without any change of context and at no cost, financial markets are first nonstationary in the medium term, preventing the use of long windows of data, and then they host feedback loops that often prevent learning without paying any cost. As a consequence, part of the literature focuses on using simulation environment (Ganesh et al, 2019;Baldacci et al, 2022;Karpe et al, 2020;Vyetrenko et al, 2020;Amrouni et al, 2021;Ritter, 2017). It allows offline training as long as desired before using the learned control, but it relies on the accuracy of the simulator.…”

Section: Introductionmentioning

confidence: 99%

“…As a consequence, part of the literature focuses on using simulation environment (Ganesh et al., 2019; Guéant & Manziuk, 2019; Baldacci et al., 2022; Karpe et al., 2020; Vyetrenko et al., 2020; Amrouni et al., 2021; Ritter, 2017). It allows offline training as long as desired before using the learned control, but it relies on the accuracy of the simulator.…”

Section: Introductionmentioning

confidence: 99%

Improving reinforcement learning algorithms: Towards optimal learning rate policies

Mounjid¹,

Lehalle²

2023

Mathematical Finance

View full text Add to dashboard Cite

This paper shows how to use results of statistical learning theory and stochastic algorithms to have a better understanding of the convergence of Reinforcement Learning (RL) once it is formulated as a fixed point problem. This can be used to propose improvement of RL learning rates. First, our analysis shows that the classical asymptotic convergence rate is pessimistic and can be replaced by with , and N the number of iterations. Second, we propose a dynamic optimal policy for the choice of the learning rate used in RL. We decompose our policy into two interacting levels: the inner and outer levels. In the inner level, we present the PASS algorithm (for “PAst Sign Search”) which, based on a predefined sequence of learning rates, constructs a new sequence for which the error decreases faster. The convergence of PASS is proved and error bounds are established. In the outer level, we propose an optimal methodology for the selection of the predefined sequence. Third, we show empirically that our selection methodology of the learning rate outperforms significantly standard algorithms used in RL for the three following applications: the estimation of a drift, the optimal placement of limit orders, and the optimal execution of a large number of shares.

show abstract

Get real

Cited by 24 publications

References 18 publications

Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks

Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks

Market-GAN: Adding Control to Financial Market Data Generation with Semantic Context

Improving reinforcement learning algorithms: Towards optimal learning rate policies

Contact Info

Product

Resources

About