Strategy #0000000151 · Machine learning
Online portfolio multiplicative-update scenario
Enter three periods of returns for three assets, follow/fade mode, learning rate and turnover cost.
Online portfolio selection updates weights as price relatives arrive without assuming a fixed return distribution. Multiplicative updates can increase recent winners or contrarily favour laggards; regret guarantees depend on the algorithm and assumptions. This tool demonstrates a no-look-ahead three-asset, three-period update with manual returns; it does not implement Cover’s universal portfolio or OLMAR.
Uses only three manual periods; no long-run regret, missing data or out-of-sample robustness is assessed.
Three ways in
Understand the story. Then inspect the risk.
Start with a familiar situation, check the payoff, then test how the numbers change.
The idea · in two minutes
How do winner-following and contrarian updates perform after turnover costs using only prior returns?
Online portfolio selection updates weights as price relatives arrive without assuming a fixed return distribution. Multiplicative updates can increase recent winners or contrarily favour laggards; regret guarantees depend on the algorithm and assumptions. This tool demonstrates a no-look-ahead three-asset, three-period update with manual returns; it does not implement Cover’s universal portfolio or OLMAR.
Enter three periods of returns for three assets, follow/fade mode, learning rate and turnover cost.
Uses only three manual periods; no long-run regret, missing data or out-of-sample robustness is assessed.
- Input assumptionsEnter three periods of returns for three assets, follow/fade mode, learning rate and turnover cost.
- Model outputUses only three manual periods; no long-run regret, missing data or out-of-sample robustness is assessed.
Illustrative research examples only. They are not live signals or a recommendation.
The mechanics · payoff and exposure
w_{i,t+1}\propto w_{i,t}(1+r_{i,t})^{\eta}\; (follow winner)
The current realised return updates weights for the next period; η controls update strength.
Greeks: the directional intuition
- 模型
- Measures sensitivity to implied volatility.
- 合約
- Measures sensitivity to implied volatility.
- 執行
- Measures sensitivity to implied volatility.
w_{i,t+1}\propto w_{i,t}(1+r_{i,t})^{\eta}\; (follow winner)
Practical context · published observations
Online portfolio multiplicative-update scenario: read the record with its caveats.
The chart uses the published figures or explicitly labelled study inputs below. A historical index or model replay is not the same as an investor’s realised account return.
Uses only three manual periods; no long-run regret, missing data or out-of-sample robustness is assessed. Source ↗ · Methodology ↗
Change assumptions and inspect the scenario
Inputs illustrate the strategy mechanics; they are not live quotes, forecasts or investment advice.
Variants · same family, different risk levers
Models, contract terms and implementation can change results.
Compare relevant mechanisms and execution assumptions.
| Related strategy | Relationship | What changes | New cost or risk |
|---|---|---|---|
| Base scenario | Manual inputs | Online portfolio selection updates weights as price relatives arrive without assuming a fixed return distribution. Multiplicative updates can increase recent winners or contrarily favour laggards; regret guarantees depend on the algorithm and assumptions. This tool demonstrates a no-look-ahead three-asset, three-period update with manual returns; it does not implement Cover’s universal portfolio or OLMAR. | Uses only three manual periods; no long-run regret, missing data or out-of-sample robustness is assessed. |
| Conservative version | Higher cost/loss | Stress higher costs, larger losses or lower liquidity. | May lower scenario returns. |
| Validation version | Data review | Test model inputs with consistent contracts and timestamps. | Needs licensed, representative data. |
Uses only three manual periods; no long-run regret, missing data or out-of-sample robustness is assessed.
Read beyond the summary
References
Primary sources and research used to describe the strategy and its limits.
- 01Cover (1991), Universal Portfoliosresearch