Forecasting Commodity Price Shocks Using Temporal and Semantic Fusion of Prices Signals and Agentic Generative AI Extracted Economic News

Paper: arXiv 2508.06497

Authors: Mohammed-Khalil Ghali, Cecil Pang, Oscar Molina, Carlos Gershenson-Garcia, Daehan Won

Abstract

Accurate forecasting of commodity price spikes is vital for countries with limited economic buffers, where sudden increases can strain national budgets, disrupt import-reliant sectors, and undermine food and energy security. This paper introduces a hybrid forecasting framework that combines historical commodity price data with semantic signals derived from global economic news, using an agentic generative AI pipeline. The architecture integrates dual-stream Long Short-Term Memory (LSTM) networks with attention mechanisms to fuse structured time-series inputs with semantically embedded, fact-checked news summaries collected from 1960 to 2023. The model is evaluated on a 64-year dataset comprising normalized commodity price series and temporally aligned news embeddings. Results show that the proposed approach achieves a mean AUC of 0.94 and an overall accuracy of 0.91 substantially outperforming traditional baselines such as logistic regression (AUC = 0.34), random forest (AUC = 0.57), and support vector machines (AUC = 0.47). Additional ablation studies reveal that the removal of attention or dimensionality reduction leads to moderate declines in performance, while eliminating the news component causes a steep drop in AUC to 0.46, underscoring the critical value of incorporating real-world context through unstructured text. These findings demonstrate that integrating agentic generative AI with deep learning can meaningfully improve early detection of commodity price shocks, offering a practical tool for economic planning and risk mitigation in volatile market environments while saving the very high costs of operating a full generative AI agents pipeline.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 8.5/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced deep learning architectures (dual-stream LSTM with attention, news embeddings) and statistical evaluation (AUC, ablation studies), while demonstrating substantial empirical rigor through a 64-year dataset, real-world data integration, and direct comparisons against established baselines.

Research Flowchart

  flowchart TD
  A["Research Goal<br>Forecast Commodity Price Shocks"] --> B["Data & Inputs<br>Prices (1960-2023) & Economic News"]
  B --> C["Methodology<br>Agentic GenAI for News Extraction"]
  C --> D["Computational Process<br>Dual-Stream LSTM + Attention Fusion"]
  D --> E["Key Outcomes<br>High Accuracy (0.91) & AUC (0.94)"]
  E --> F["Insight<br>News Context is Critical for Performance"]

Cited References (33)

1. Crude Oil Price Forecasting Techniques: A Comprehensive Review of Literature (2013)
2. Forecasting the Real Price of Oil in a Changing World: A Forecast Combination Approach (2015)
3. An Assessment of Time Series Methods in Metal Price Forecasting (2005)
4. Forecasting the COMEX Copper Spot Price by Means of Neural Networks and ARIMA Models (2015)
5. Forecasting Crude Oil Prices: A Comparison Between Artificial Neural Networks and Vector Autoregressive Models (2019)
6. Forecasting Commodity Prices: Looking for a Benchmark (2021)
7. Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005–2019 (2020)
8. A Deep Learning Ensemble Approach for Crude Oil Price Forecasting (2017)

1 of 33 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.