A dual-stream LSTM with attention is claimed to forecast commodity price shocks with 0.94 AUC using price data and LLM-generated news summaries, but the evaluation has look-ahead leakage.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.CP 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Forecasting Commodity Price Shocks Using Temporal and Semantic Fusion of Prices Signals and Agentic Generative AI Extracted Economic News
A dual-stream LSTM with attention is claimed to forecast commodity price shocks with 0.94 AUC using price data and LLM-generated news summaries, but the evaluation has look-ahead leakage.