Simulating and Optimizing Public Fund Holdings

Summary

The article outlines a workflow for reconstructing and simulating a Chinese public fund’s equity holdings. It scrapes disclosed stock codes and portfolio weights for a China Merchants CSI 300 enhanced index fund, then assumes quarterly rebalancing: the reported holdings and weights are applied at the quarter end and held through the disclosure date. The article says this simulated period return was -5.31%, broadly matching a market-data application’s figure for the same period.

It then describes an AI-based reweighting approach. A template strategy’s factors are used to train a model on 2010–2015 data; the model ranks stocks in the reported holdings universe and the portfolio is periodically rebalanced based on those rankings. The article reports a -2.88% simulated return for this optimized version and characterizes it as an improvement. The evidence is limited to this example and period: details on costs, benchmark-relative risk, validation design, and robustness are not supplied, so the reported enhancement does not establish general performance.

Key ideas

• The workflow scrapes publicly disclosed stock codes and weights for a fund portfolio.
• The baseline simulation applies reported weights and assumes quarterly holding and rebalancing.
• A factor-based model trained on 2010–2015 data ranks stocks within the disclosed holdings universe.
• The article reports -5.31% for the baseline simulation and -2.88% for the optimized simulation.
• The example does not establish robustness across funds, periods, costs, or validation methods.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.