Making Online Portfolio Selection Robust to Live Trading Constraints

Summary

This note describes the gap between theoretical online portfolio selection (OLPS) models and live implementation. It points to assumptions often used in research, such as no transaction fees or market impact, ample liquidity, and the ability to trade arbitrary share quantities. The author reports that strategies which performed well without fees became unprofitable once fees exceeded 0.1%.

Live portfolios also diverge from target weights when trades incur fees, exchange quantity rules require rounding, network or maintenance problems prevent orders, or fills are partial or absent. The author says a month of live trading produced a severe decline, but gives no strategy details, market, or independent performance analysis. The account highlights the need to model trading frictions and operational disruptions; it does not provide a tested method for adapting OLPS to those constraints.

Key ideas

• Many OLPS models assume away fees, market impact, liquidity limits, and quantity constraints.
• The author reports that some fee-free strategies lost profitability once fees exceeded 0.1%.
• Fees, rounding, outages, and incomplete fills can cause actual portfolio weights to drift from model targets.
• Live results over a month are presented as an anecdote without enough detail to assess generality.
• The document raises the implementation problem but offers no validated adaptation method.

Tags

# OLPS in real conditions


# OLPS in real conditions












The Online Portfolio Selection problem has been extensively researched over the years, and various models have been implemented in open-source projects on GitHub. However the theoretical frameworks of the papers are quite convenient for their authors and make assumptions that are incompatible with real-life trading (no transaction fees and impact costs, perfect market liquidity, buying & selling arbitrary quantities of shares...).

As expected, I found multiple strategies that work well without transaction fees but whose performance degrade rapidly, being unprofitable with more than 0.1% of fees.

Also, in production, it is possible to rebalance the weights :

- after a buy/sell sequence to account for the fees;

- after rounding to the shares' quantities accepted by the exchange;

- after network issues, server maintenances... where orders didn't go through;

- after no/partial order execution;

- ...

All these real-life constraints bring us away from the optimal solution of the model implemented in the algo. I confirmed it live over the course of a month: a spiral down to hell. What is the point of implementing and tweaking the best state-of-the-art model if it only works in utopic conditions and is going to be wrecked in real-life? I could not find any guidelines on adapting OLPS models to live trading, any insight would be welcome.

Thanks!

Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)

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