CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News

📰 ArXiv cs.AI

CN-Buzz2Portfolio is a dataset and benchmark for evaluating LLM-based macro and sector asset allocation in the Chinese market using daily trending financial news

advanced Published 25 Mar 2026
Action Steps
  1. Collect and preprocess daily trending financial news data from the Chinese market
  2. Develop and train LLM-based models for macro and sector asset allocation using the CN-Buzz2Portfolio dataset
  3. Evaluate the performance of the models using the provided benchmark
  4. Refine and fine-tune the models to improve their decision-making capabilities
Who Needs to Know This

Quantitative analysts and AI researchers on a team can benefit from this dataset to develop and evaluate LLM-based financial decision-making models, while data scientists can utilize it to fine-tune their models for better performance

Key Insight

💡 The CN-Buzz2Portfolio dataset and benchmark enable the evaluation and development of LLM-based financial decision-making models in a reproducible and unbiased manner

Share This
📊 LLMs for finance: CN-Buzz2Portfolio dataset & benchmark for macro & sector asset allocation
Read full paper → ← Back to News