Tag
This paper presents a language model forecasting system for merger arbitrage that combines expert-guided context engineering with fine-tuning on historical deals, achieving state-of-the-art performance on over 400 large deals across 42 countries.
This paper investigates how different inference-time deployment rules (rollout strategies) impact multi-horizon volatility forecasting. It shows that non-default rollout rules often improve performance and that validation-based deployment policies provide a low-cost improvement over standard MIMO deployment, emphasizing the importance of deployment policy alongside model architecture.
MOSAIC introduces a structured agentic framework for automated data science that uses memory-grounded model selection and workflow construction, validated on financial time-series tasks. It outperforms AutoML and agentic baselines.
Proposes a bi-level chaotic fusion based graph convolutional network for stock market prediction intervals, achieving significant improvements in Winkler score, PIAW, and PICP over baselines on NSE data from 2016-2026.