Neumann Eyal

Imperial College

Abstract: We model a market with multiple dealers who compete for client order flow by dynamically updating their bid an offer quotes for a risky asset. The dealers aim to maximize expected profits while controlling for the risk on their inventory holdings by skewing their quotes to attract opposing interest (internalisation) or by directly offloading positions in the open market (externalisation). Using a variational approach, we derive a closed-form equilibrium for the resulting Nash competition, shedding light on fundamental phenomena in the dynamics of dealer markets. We show that internalising dealers are forced to increase their externalisation activity when they are put in competition with other externalising dealers. This strategic shift of the equilibrium ultimately lowers the P&L for all dealers in the market and leads to substantial increased spread costs for clients.  

Silvia Trimarchi

A2A SpA

Abstract: The energy markets are experiencing an enhanced volatility and unpredictability due to the growing integration of renewable energy sources in the grid and to the unstable geopolitical situation that is developing worldwide. Energy traders are therefore raising concerns on how to achieve solutions that not only ensure stability in terms of energy needs, both on the supply and demand side, but also enable profits within these markets. To cope with the complexity of this emerging scenario, tools that support traders in their decisions, such as algorithmic trading strategies, are attracting always more and more attention. In particular, evolutionary algorithms have emerged as an effective tool for developing robust and innovative trading strategies. Indeed, their flexibility and adaptability allow for the inclusion of various performance metrics. This article employs a recently issued evolutionary algorithm, called social network optimization, to identify the optimal closing criteria of already opened positions in an energy commodity market. More specifically, the proposed trading strategy is based on five self-defined parameters, which determine a profitable solution over nearly six years of available data. In particular, the overall average positive return achieved and the maximum monthly yield of 1.9% highlight the adaptability and robustness of the developed algorithmic trading strategy. Therefore, the results suggest the potentialities of developing and upgrading novel trading strategies by exploiting evolutionary computation techniques in the actual complex energy markets.

Roxana Halbleib

University of Freiburg

Abstract: This paper examines the forecast combination for Value-at-Risk (VaR) and Expected Shortfall (ES). We show that the weighted arithmetic average commonly used to construct a forecast combination utilises the convexity property of the loss function only in case of VaR, while to combine ES one should use the harmonic mean. 
To construct combination weights consistent with this aggregation result, we propose a novel forecast combination for tail risk measures based on the Bagged Pretested Forecast Combination (BPFC) algorithm.
The combination weights assigned to candidate models are determined by their predictive performance using the Model Confidence Set (MCS) test. Unlike many traditional combination methods, BPFC adapts to changing market conditions while simultaneously facilitating model selection and improving forecast stability. We evaluate the performance of forecasting combinations for VaR and ES within the framework of consistent loss functions, highlighting the role of convexity in performance improvements. Our results show that the advantages of combining forecasts are especially evident when there is substantial disagreement among candidate models, a situation that commonly arises during turbulent financial periods.
To empirically validate our approach, we apply it to a dataset of 90 stocks spanning various market capitalizations and covering periods of severe financial stress, including the Global Financial Crisis and the COVID-19 pandemic. The results illustrate the ability of BPFC to dynamically select and combine the most effective models from a pool of over 60 candidates, continuously adjusting weights based on model’s forecasting performance and evolving market conditions.

Aldo Glielmo

Research Scientist, Banca d'Italia

Abstract: Reinforcement learning (RL) is emerging as a powerful tool for economic modelling, enabling agents to learn optimal strategies through interaction with simulated environments, rather than relying on pre-specified behavioural rules or rational expectations as typical in traditional approaches. In my talk, I will showcase recent work on integrating RL agents into macroeconomic models to study agents’ rationality and heterogeneity [Brusatin et al., ICAIF 2024; Gabriele et al., AAMAS 2026], deploying them in applications involving natural-gas market [Balaconi et al., ICAIF 2025], and improving their robustness to model misspecification for policy design [Agrawal et al., MARW@AAAI 2025]. I will demonstrate that RL agents can spontaneously discover different utility-maximisation strategies and can replicate real-world market behaviours. While these advances point toward a promising new modelling paradigm, realising its full potential will require continued progress on validation, robustness, and computational scalability.

Gaia Salford - Head of Multiasset, Investments
Michele Carone - Quant Fund Selector, Investment Strategy and Delegated Asset Managers

Banco Posta Fondi Spa SGR

Abstract: This work investigates the relationship between social media information flows and financial market dynamics, proposing an exploratory framework to assess whether digital sentiment may contribute to investment decision-making.
We collect and process large-scale textual data from online social platforms, applying natural language processing techniques to construct topic clusters and related sentiment indicators. These indicators are statistically analyzed alongside stock market returns. The study investigates both contemporaneous relations and lagged effects to identify potential predictive patterns. Based on the empirical findings, we design and backtest a sentiment-driven equity trading strategy. The results fit within the broader investigation of behavioral finance, tentatively seeking to complement the information set available to professional investors by considering the potential impact that the intensity of this emerging information channel may exert on asset prices.

Federico Bianchi
Roberta Piersimoni

Financial Risk Management, CDP

Abstract: Counterparty Credit Risk (CCR) is the risk that a financial counterparty fails to meet its obligations on derivatives, treasury transactions, or other operations whose value changes over time. It represents, for all financial institutions, a critical risk to be managed because it directly affects capital stability, the ability to contain unexpected losses, and the overall soundness of exposures - combining elements of creditworthiness with market risks and introducing the need to consider the so-called Value Adjustments (CVA, DVA, …).
Supervisory regulation has evolved over time (Basel 3.5 and 4, Capital Requirements Directive EU/36/2013 and Capital Requirements Regulation EU/575/2013), establishing methods and criteria for measuring counterparty risk and calculating capital absorption.
For this type of risk, Exposure at Default (EaD) and credit equivalent (or analogous Potential Future Exposures…) allow derivative and collateralized transactions to be conceptually converted into an exposure comparable to traditional credit risk.
From a regulatory perspective, the SA-CCR methodology provides the standardized formula for estimating the exposure of off-balance sheet items, combining replacement cost and potential future exposure with specific coefficients depending on instrument type and maturity.
Master agreements (ISDA and CSA, GMRA) define netting sets and collateralization rules, which are essential for reducing effective credit exposure. Likewise, the role of central counterparties is crucial for mitigating and managing counterparty risk.