arXiv subjects

Anahí Rodríguez-Martínez

Publications and source records attributed to Anahí Rodríguez-Martínez.

2 recordsLinked to original sources

arXiv2026

Is Bitcoin A Hedge Against Central Banking? Evidence from AI-Driven Monetary Policy Expectations

This study investigates the transmission of monetary policy narratives to Bitcoin prices, distinguishing policy expectations from realized policy implementation. We introduce a weekly Monetary Policy Expectations (MPE) index derived from the Large Language Model (LLM)-based classification of 118,000+ market messages, providing a granular measure of hawkish and dovish monetary policy discourse. We demonstrate that changes in the MPE index provide evidence of significant linear predictive information for Bitcoin returns at short-to-medium horizons, with significant Granger causality at multiple lags. A Long Short-Term Memory (LSTM) framework combined with SHapley Additive exPlanations (SHAP) further identifies nonlinear and regime-dependent relationships between monetary-policy expectations and Bitcoin returns, indicating that Bitcoin functions as a sensitive barometer of central bank signaling. In particular, hawkish monetary-policy narratives are associated with negative price responses that are not accounted for by contemporaneous Federal Funds Rate adjustments. These findings highlight Bitcoin's structural sensitivity to global monetary discourse, establishing LLM-derived monetary-policy sentiment as a high-frequency measure of central-bank communication and as an informative leading macroeconomic indicator for the digital asset landscape.

econ.GN↗

arXiv2025

DebtStreamness: An Ecological Approach to Credit Flows in Inter-Firm Networks

Understanding how credit flows through inter-firm networks is critical for assessing financial stability and systemic risk. In this study, we introduce DebtStreamness, a novel metric inspired by trophic levels in ecological food webs, to quantify the position of firms within credit chains. By viewing credit as the ``primary energy source'' of the economy, we measure how far credit travels through inter-firm relationships before reaching its final borrowers. Applying this framework to Uruguay's inter-firm credit network, using survey data from the Central Bank, we find that credit chains are generally short, with a tiered structure in which some firms act as intermediaries, lending to others further along the chain. We also find that local network motifs such as loops can substantially increase a firm's DebtStreamness, even when its direct borrowing from banks remains the same. Comparing our results with standard economic classifications based on input-output linkages, we find that DebtStreamness captures distinct financial structures not visible through production data. We further validate our approach using two maximum-entropy network reconstruction methods, demonstrating the robustness of DebtStreamness in capturing systemic credit structures. These results suggest that DebtStreamness offers a complementary ecological perspective on systemic credit risk and highlights the role of hidden financial intermediation in firm networks.

econ.GN↗