Online Portfolio Selection Benchmarks and Their Limits
Summary
This introduction compares four portfolio selection benchmarks using a collection of 23 ETFs with closing prices from 2008 to 2016. Buy and Hold starts with fixed allocations and lets weights drift with asset prices; Best Stock selects the strongest asset with hindsight; Constant Rebalanced Portfolio restores chosen weights each period; and Best Constant Rebalanced Portfolio optimizes fixed weights using the full historical sequence. The examples contrast passive allocation, rebalancing, and hindsight optimization.
In this dataset, the hindsight optimizer favors technology equities and long-term Treasury exposure, and monthly rebalancing produces slightly higher returns than daily rebalancing. These results are historical illustrations, not live-trading evidence. Best Stock and Best Constant Rebalanced Portfolio rely on future information and cannot be implemented as described in real time. The article also notes that transaction costs would reduce rebalanced portfolio returns, and that benchmark performance depends on the selected assets, period, and allocation.
Key ideas
- Buy and Hold allows portfolio weights to drift as asset prices change.
- A Constant Rebalanced Portfolio repeatedly restores its target weights, which can shift capital from rising assets toward falling ones.
- Best Stock and Best Constant Rebalanced Portfolio use hindsight and serve as comparison benchmarks rather than directly implementable live strategies.
- Rebalancing frequency can affect historical results, while transaction costs can reduce the benefits of frequent rebalancing.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.