Alexandre Moulti
Paris et périphérie
1 k abonnés
+ de 500 relations
Expérience
Formation
-
Ecole Polytechnique Executive Education
-
-
My validation project consisted in realizing a credit scoring of corporates thanks to the use of financial statements and market information by using IA techniques. This enables to translate instantly the market information into a credit score which accelerates the process of decision making.
-
-
-
-
-
-
-
-
-
-
-
Autres profils similaires
Découvrir plus de posts
-
IICPC(InterCollegiate Informatic and Competitive Programming Camp Pvt Ltd)
IMC Trading at IICPC Codefest 2026! We’re excited to share that IMC Trading will be a partner in IICPC Codefest 2026! While we won’t reveal the partnership tier just yet (we’ll let you guess 🙂), we’re confident this collaboration will be especially valuable for students aspiring to internships in Software Engineering and Quantitative Research/Trading domains. IMC Trading is a leading global market maker, leveraging technology, mathematics, and data-driven strategies to make markets more efficient. Most of their software and technology work happens in India, where teams build cutting-edge systems that power trading across the world. This makes IMC a unique place where talented students can experience real-world applications of coding, algorithms, and quantitative research. IMC Trading is actively involved in Quantfest 2025, mentoring participants and scouting talent. They would be keeping an eye on everyone’s software skills in Codefest as well. With the addition of IICPC Quantfest to Codefest 2026, there’s even more opportunity for students to showcase their abilities to a leading global market maker. Thanks to Manikantan MVL for continuous support,collaboration and leading growth of IMC Trading in India. We’ll share the stats post-November!
-
Norbert Gehrke
Bank of England - Measuring the stability of the banking system This study develops a stochastic balance sheet based microstructural banking model to quantify the dynamic interplay between solvency and liquidity risks – two traditionally distinct dimensions in stress testing. By incorporating endogenous bank reactions, feedback loops, and amplification mechanisms, the model captures how management responses to shocks can escalate financial distress, potentially leading to insolvency and illiquidity. The authors apply the model to granular loan and security exposure data from UK banks over 2015–24, estimating capital and liquidity at risk and deriving a systemic default probability indicator. Results indicate an average one-year bank default probability of 0.7%, consistent with market-implied estimates but diverging during stress episodes. Amplification effects, driven by balance sheet constraints and behavioural responses, account for approximately one third of default risk on average. Counterfactual analyses further evaluate the effectiveness of capital requirements and identify optimal capital levels under hypothetical stress scenarios.
2 commentaires -
Yash Y.
AlphaAgents: Multi-Agent LLMs for Equity Portfolio Construction — and what happens when you plug in institutional sentiment + data feeds Just read AlphaAgents, a fresh paper from BlackRock researchers exploring role-based, debate-driven LLM agents for systematic stock selection and portfolio construction. The system mirrors a real investment team with three specialists that collaborate and argue their way to a decision: Fundamental Analyst, Sentiment Analyst, and Valuation Analyst. - What’s novel 1. Role specialization + debate: Agents run in a group-chat workflow (AutoGen) and must reach consensus, which helps reduce hallucinations and surfaces assumptions. 2. Risk-aware behavior: Recommendations are explicitly conditioned on investor risk tolerance (risk-seeking / neutral / averse), not just point estimates. 3. Tool-augmented analysis: - Fundamental agent uses a tailored 10-K/10-Q RAG tool; - Sentiment agent summarizes and critiques news before opining; - Valuation agent computes returns/vol and reads price/volume structure. 4. Evaluation signals: They treat back-testing as a downstream metric, in addition to task-level checks. - Why it matters This architecture is auditable, modular, and closer to how human teams actually work—diverse priors, debate, and a clear hand-off into portfolio construction. It also offers a path to mitigate cognitive biases (loss aversion, overconfidence) that creep into discretionary workflows. - Now imagine the next step Pair AlphaAgents’ workflow with institutional-grade sentiment and deep data coverage: real-time news/analyst-notes + FactSet fundamentals + PitchBook private-market context + filings + broker research. Then fine-tune or retrain reasoning models on domain-specific corpora (sentiment events, accounting footnotes, sector playbooks). The result is a futuristic portfolio management copilot that feels AGI-like in practice: - Unified data fabric (EDGAR, news, FactSet, PitchBook) → cleaned, labeled, time-aligned - Hybrid retrieval (RAG + knowledge graph) to ground every claim - Multi-agent committee (Fundamental / Sentiment / Valuation + Macro / Risk / ESG extensions) with debate + confidence scores - Risk & compliance layer (limits, exposure, scenario analysis) gating trades - Optimizer (MV, Black-Litterman, risk parity, or RL) consuming agent views - Monitoring (drift, rationale tests, counterfactuals) for production safety This is how we move from “LLM that chats” to institutional-grade, explainable, end-to-end portfolio decisioning. Paper: Attached! #AI #MultiAgent #LLM #QuantFinance #PortfolioConstruction #RAG #AutoGen #Research #FactSet #PitchBook #SentimentAnalysis #RiskManagement #AGI #AIFinance #ArtificialIntelligence #ResearchAI
1 commentaire -
Hugo Delatte
Schur Complementary Allocation is now part of skfolio v0.13.0. Thanks to Peter Cotton for his contribution and review! This allocation method uses Schur-complement-inspired augmentation of sub-covariance matrices to smoothly interpolate between Hierarchical Risk Parity (HRP) and the Minimum-Variance Portfolio (MVP). HRP, which leverages hierarchical clustering, tends to yield more diversified and stable allocations than MVP, which is more sensitive to estimation error and can produce concentrated weights. Schur Complementary Allocation allows us to explore the continuum between them by tuning a regularization factor that controls how much off-diagonal information is incorporated into the augmented covariance blocks. We can then leverage the scikit-learn toolkit using randomized search cross-validation to select the regularization factor that maximizes a chosen out-of-sample portfolio metric. A key implementation focus was numerical robustness, maintaining a well-conditioned covariance matrix across the regularization path. Example in the comments below. #skfolio #opensource #machinelearning #portfoliooptimization #quantitativefinance #quant #portfoliomanagement
7 commentaires -
Nam Nguyen, Ph.D.
Hedge Effectiveness Under a Four-State Regime Switching Model Machine learning methods often face challenges of interpretability, overfitting, and a lack of robustness in real-world deployment. The paper proposed a more “classical” regime identification technique. It developed a four-state regime switching (PRS) model for FX hedging. Findings -The authors develop a four-state regime-switching model using forward contracts to hedge foreign exchange positions. -The PRS model reduces portfolio variance more effectively than existing hedging strategies in the dollar, euro, yen, and lira markets. -In the rupee market, the model delivers the second-best performance among tested approaches. -The results suggest that optimizing the memory level in the four-state regime-switching model produces better hedging outcomes than applying a constant hedge ratio across the entire period. -The findings align with prior research advocating for models that update with more recent data over time. -The superior performance of the proposed model relative to other dynamic approaches indicates its ability to capture asymmetry and fat-tail characteristics common in FX returns. -The particularly strong results for the lira imply that the model is especially effective for highly volatile currencies. -The model adjusts the estimation horizon dynamically, allowing it to determine the optimal hedge ratio under prevailing market conditions. Reference: Taehyun Lee, Ioannis C. Moutzouris, Nikos C. Papapostolou, Mahmoud Fatouh, Foreign exchange hedging using regime-switching models: The case of pound sterling, Int J Fin Econ. 2024;29:4813–4835. Join a community of 6,000+ quants—subscribe to the newsletter! Link in profile #hedging #riskmanagement #portfoliomanagement ABSTRACT We develop a four-state regime-switching model for optimal foreign exchange (FX) hedging using forward contracts. The states correspond to four distinct market conditions, each defined by the direction and magnitude of deviation of the prevailing FX spot rate from its long-term trends. The model's performance is evaluated for five currencies against the pound sterling for various horizons. Our examination compares the hedging outcomes of the proposed model to those of other commonly employed hedging methods. The empirical results suggest that our model demonstrates the highest level of risk reduction for the US dollar, euro, Japanese yen and Turkish lira and the second-best performance for the Indian rupee. The risk reduction is significantly higher for lira compared with the other approaches, implying that the proposed model might be able to provide much more effective hedging for highly volatile currencies. The improved performance of the model can be attributed to the adjustability of the estimation horizon for the optimal hedge ratio based on the prevailing market conditions. This, in turn, allows it to better capture fat-tail properties that are frequently observed in FX returns...
1 commentaire