Research Paper on Explainable AI for Economic Mental Health Forecasting

A 70.7 KB PDF document authored by Ying Yang, last updated on April 27, 2026. The paper proposes a novel framework integrating explainability directly into time series prediction for economic mental health analysis. It discusses methods combining feature attribution and causal reasoning to improve model interpretability while maintaining accuracy.

Use Cases

• Developing interpretable time series forecasting models based on the described framework for feature attribution and causal reasoning.
• Benchmarking explainable AI (XAI) techniques in mental health analytics based on the proposed intrinsic and post-hoc interpretability methods.
• Informing policy decisions for mental health screening based on the paper's discussion of transparent, AI-driven tools.

Strengths

• Document is under a permissive CC-BY-4.0 license.
• File size is precisely 70.7 KB, indicating a concise, focused document.

Limitations

• The dataset is a single PDF document, not a structured data collection.
• Row count and column definitions are unknown, limiting direct data utility.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Ying Yang via figshare

Collection Method

Proposed research framework and experimental results documented in a paper.

Time Range

Publication date implied as 2026.

Freshness

Last updated 2026-04-27 13:42:09; freshness should be verified.

Geography

null