Back to Community
Market Panic: Parameter-Optimized Strategy for Lay Investors

In August, we saw a substantial market correction, which prompted an interesting analysis by 538 on whether to sell or to hold during a market panic, i.e. when the S&P suffers a big decline. The folks at 538 propose that holding your assets is better than selling during the panic and buying back later.

To illustrate the point, they simulated a trader who sold SPY upon downturns of 5% and bought back upon rebounds of 3%. But that's just one set of parameters, so I wrote an algorithm to let users test out any variant of this strategy.

Going further, I wanted to find out whether a variant of this strategy exists that a lay investor (which I loosely think of as a person who does not have the time or resources to create a sophisticated trading strategy, and instead makes decisions simply based on SPY price movements) can use to beat the market, especially in times of economic downturn.

To do this, I ran over 5000 different backtests, iterating over a vast variety of possible drawdown and rebound values. My results showed that such a parameter-optimized strategy can generate significantly market-beating returns. However, closer inspection revealed that this was solely a consequence of its superior performance during the recession, and that the parameters were effectively dangerously overfit to this single event. I do not think that the next economic downturn will be similar enough to the previous ones for these optimized parameters to be useful for prediction. As such, I conclude -- perhaps unsurprisingly -- that there's no simple strategy to ensure market-beating returns in times of economic downturn. I end up agreeing with the folks at 538: if you're invested in SPY and don't have the opportunity to construct a sophisticated strategy, you may as well hold on to it.

Loading notebook preview...
3 responses

Excellent and thorough work! The nearest strategy I've seen for a lay investor to improve on buy-and-hold is Meb Faber's GTAA paper, which also compares some parameters.

Thanks for the positive feedback and the reference.

If it is too close to call, then when considering instances where taxes are involved, the buy and hold would win hands down.