Namid Stillman
Namid Stillman has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Andreea Bacalum
Simudyne, London, United Kingdom
2 shared publications - Ollie Olby
Simudyne, London, United Kingdom
2 shared publications - Perukrishnen Vytelingum
Simudyne Limited, United Kingdom
2 shared publications - Rory A. Baggott
The John Adams Institute for Accelerator Science, Imperial College London, London, UK
2 shared publications - Carmine Ventre
King's College London, London, United Kingdom
1 shared publication - Ce Guo
Imperial College London, London, United Kingdom
1 shared publication
Latest Publications
- Open Access
- 13 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1276-1284
FlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching
- 13 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1276-1284
Open AccessFlowLOB: Efficient and Controllable Limit Order Book Generation with Flow Matching
- Open Access
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 898-905
Right Place, Right Time: Market Simulation-based RL for Execution Optimisation
- 14 November 2025
- Published by Association for Computing Machinery (ACM)
- p. 898-905
Open AccessRight Place, Right Time: Market Simulation-based RL for Execution Optimisation
- Open Access
- 10 September 2024
- Published by Wiley in The Geographical Journal
- Vol. 191 (1)
Where the wild places are: Factors associated with people's favourite local and national wild place in the United Kingdom
Protected areas globally serve as crucial sanctuaries for biodiversity, playing a pivotal role in conserving endangered species and maintaining ecological balance. In the United Kingdom (UK), 25% of land is currently designated as public protected areas and discussions are underway regarding the implementation of new protected areas, including the establishment of new National Parks in all four nations of the UK. Wild places have an important role to play in understanding and deciding where public protected areas should or could be. People form profound connections to wild places locally and nationally. We used two online surveys to gather information on the UK public's local and national favourite wild places, and the characteristics of those places which make them their top choice. Our analysis revealed that respondents preferred different wild places based on their survey group, with significant differences in the importance placed on characteristics like ‘Accessibility’, ‘Nature’ and ‘Scenery’ across local and national scales. Demographic factors, including age and settlement, had some impact, but the overall importance of characteristics like ‘Peace and Quiet’ and ‘Nature’ were consistently high across both surveys. Recognising the prevalence of favourite wild places outside of designated areas underscores the importance of engaging the different viewpoints of the public in conservation initiatives, and indicates that public support for conservation might extend beyond officially protected regions.
- 10 September 2024
- Published by Wiley in The Geographical Journal
- Vol. 191 (1)
Open AccessWhere the wild places are: Factors associated with people's favourite local and national wild place in the United Kingdom
Protected areas globally serve as crucial sanctuaries for biodiversity, playing a pivotal role in conserving endangered species and maintaining ecological balance. In the United Kingdom (UK), 25% of land is currently designated as public protected areas and discussions are underway regarding the implementation of new protected areas, including the establishment of new National Parks in all four nations of the UK. Wild places have an important role to play in understanding and deciding where public protected areas should or could be. People form profound connections to wild places locally and nationally. We used two online surveys to gather information on the UK public's local and national favourite wild places, and the characteristics of those places which make them their top choice. Our analysis revealed that respondents preferred different wild places based on their survey group, with significant differences in the importance placed on characteristics like ‘Accessibility’, ‘Nature’ and ‘Scenery’ across local and national scales. Demographic factors, including age and settlement, had some impact, but the overall importance of characteristics like ‘Peace and Quiet’ and ‘Nature’ were consistently high across both surveys. Recognising the prevalence of favourite wild places outside of designated areas underscores the importance of engaging the different viewpoints of the public in conservation initiatives, and indicates that public support for conservation might extend beyond officially protected regions.
- Open Access
- 25 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 270-278
Deeper Hedging: A New Agent-based Model for Effective Deep Hedging
We propose the Chiarella-Heston model, a new agent-based model for improving the effectiveness of deep hedging strategies. This model includes momentum traders, fundamental traders, and volatility traders. The volatility traders participate in the market by innovatively following a Heston-style volatility signal. The proposed model generalises both the extended Chiarella model and the Heston stochastic volatility model, and is calibrated to reproduce as many empirical stylized facts as possible. According to the stylised facts distance metric, the proposed model is able to reproduce more realistic financial time series than three baseline models: the extended Chiarella model, the Heston model, and the Geometric Brownian Motion. The proposed model is further validated by the Generalized Subtracted L-divergence metric. With the proposed Chiarella-Heston model, we generate a training dataset to train a deep hedging agent for optimal hedging strategies under various transaction cost levels. The deep hedging agent employs the Deep Deterministic Policy Gradient algorithm and is trained to maximize profits and minimize risks. Our testing results reveal that the deep hedging agent, trained with data generated by our proposed model, outperforms the baseline in most transaction cost levels. Furthermore, the testing process, which is conducted using empirical data, demonstrates the effective performance of the trained deep hedging agent in a realistic trading environment.
- 25 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 270-278
Open AccessDeeper Hedging: A New Agent-based Model for Effective Deep Hedging
We propose the Chiarella-Heston model, a new agent-based model for improving the effectiveness of deep hedging strategies. This model includes momentum traders, fundamental traders, and volatility traders. The volatility traders participate in the market by innovatively following a Heston-style volatility signal. The proposed model generalises both the extended Chiarella model and the Heston stochastic volatility model, and is calibrated to reproduce as many empirical stylized facts as possible. According to the stylised facts distance metric, the proposed model is able to reproduce more realistic financial time series than three baseline models: the extended Chiarella model, the Heston model, and the Geometric Brownian Motion. The proposed model is further validated by the Generalized Subtracted L-divergence metric. With the proposed Chiarella-Heston model, we generate a training dataset to train a deep hedging agent for optimal hedging strategies under various transaction cost levels. The deep hedging agent employs the Deep Deterministic Policy Gradient algorithm and is trained to maximize profits and minimize risks. Our testing results reveal that the deep hedging agent, trained with data generated by our proposed model, outperforms the baseline in most transaction cost levels. Furthermore, the testing process, which is conducted using empirical data, demonstrates the effective performance of the trained deep hedging agent in a realistic trading environment.
- Open Access
- 25 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 46-54
Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks
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.
- 25 November 2023
- Published by Association for Computing Machinery (ACM)
- p. 46-54
Open AccessDeep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks
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.
- 28 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 279-282
How Spatiality Impacts In Silico Experiments of Nanoparticle-Cell Interactions
Nanomedicine, the use of nanoparticles as therapeutic or diagnostic vectors, is expected to be improved through the use of in silico methods which allow for prototype nanoparticle designs to be tested before synthesis and in vitro/in vivo validation. Here, we show that the choice of modelling framework can impact predictions of tissue penetration, focussing specifically on the role of spatial effects for nanoparticles internalised into a cell. We demonstrate that spatial reaction diffusion simulations differ from the well mixed approximation, especially when nanoparticles have large diffusion coefficient and high binding affinity. We expect these results to be of interest to both the in silico community as well as those using these models to optimise nanoparticle designs before real world validation.
- 28 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 279-282
How Spatiality Impacts In Silico Experiments of Nanoparticle-Cell Interactions
Nanomedicine, the use of nanoparticles as therapeutic or diagnostic vectors, is expected to be improved through the use of in silico methods which allow for prototype nanoparticle designs to be tested before synthesis and in vitro/in vivo validation. Here, we show that the choice of modelling framework can impact predictions of tissue penetration, focussing specifically on the role of spatial effects for nanoparticles internalised into a cell. We demonstrate that spatial reaction diffusion simulations differ from the well mixed approximation, especially when nanoparticles have large diffusion coefficient and high binding affinity. We expect these results to be of interest to both the in silico community as well as those using these models to optimise nanoparticle designs before real world validation.