---
title: The Micro-Determinants of Portfolio Gyrations in Mutual Funds: Evidence From Machine Learning Models
url: https://www.ml-quant.com/papers/ssrn/5103683/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 5103683
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5103683
featured: 2025-01-23
citations: 0
topic: Portfolio & Allocation
---


# The Micro-Determinants of Portfolio Gyrations in Mutual Funds: Evidence From Machine Learning Models

The research explores what influences portfolio changes in emerging market equity mutual funds, highlighting firm size, investment features, and stock attributes as key factors, with their significance changing based on market conditions and investment strategies.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=5103683
- Identifier: SSRN 5103683
- Released: 2025-01-20
- First featured: Quant Letter No. 83 (2025-01-23): https://www.ml-quant.com/issues/2025-01-23/
- Citations (Semantic Scholar): 0
- Published in: not yet
- Topic: Portfolio & Allocation

## Related

- [The Performance of Household-held Mutual Funds: Evidence from the Euro Area](https://www.ml-quant.com/papers/ssrn/4849419/): A study from 2009 to 2020 shows that Euro-area households prefer pricier, lower risk-adjusted return mutual funds, particularly equity funds, and tend to follow past returns.
- [Beat the Market: An Effective Intraday Momentum Strategy for S&P500 ETF (SPY)](https://www.ml-quant.com/papers/ssrn/4824172/): The study investigates the success of an intraday momentum strategy on SPY, an ETF tracking the SP500, which resulted in a 1985 total return from 2007 to 2024.
- [STRAPSim: A Portfolio Similarity Metric for ETF Alignment and Portfolio Trades](https://www.ml-quant.com/papers/arxiv/2509.24151/): STRAPSim, a new method for assessing portfolio similarity, surpasses existing measures by using semantic similarity, portfolio share weighting, and residual-aware greedy alignment, proving beneficial in ETF benchmarking, portfolio creation, and systematic execution.
- [Reaching for Duration and Leverage in the Treasury Market](https://www.ml-quant.com/papers/ssrn/4816018/): The article reveals that the use of Treasury futures by mutual funds varies significantly over time and across funds, influencing the variation in aggregate Treasury futures open interest.
- [Machine Learning Mutual Fund Flows](https://www.ml-quant.com/papers/ssrn/4812038/): Nonlinear machine learning models are more effective than linear models in predicting future fund flows, with past flows and the Morningstar rating as key predictors.
- [Who Clears the Market When Passive Investors Trade?](https://www.ml-quant.com/papers/ssrn/4777585/): The article investigates the role of firms in providing shares to passive investors, particularly in response to index funds' buying.