Working through my taxes for the last financial year I find myself constantly asking myself why I made the trades I did. What strategy was I using? I haven’t been keeping the kinds of record that some tutors recommend. Which brings me to something very fundamental to trading strategies – backtesting.
I’ve done a lot of backtesting in the past. All by the book, coming up with excellent Sharpe ratios and significant projected profits. But when I actually start trading, not so much. In fact I’ve become convinced that backtesting, at least in crypto, is a complete waste of time.
And it’s not just backtesting. My current strategy is a standard stat arb mean reversion, using pairs that are cointegrated at the 99% level by two different tests on the past year of data. I enter a trade when it’s 2 SDs from the mean, only to have it move more than 4 SDs from the mean almost immediately, in the wrong direction. And not just one pair. I’ve decided to diversify as much as the available pairs will allow, and out of 20 such pairs about 16 of them have exhibited the above behaviour, while the profits I make on the few properly behaved pairs are tiny in comparison. Some of my pairs have been running for months, waiting for mean reversion. Well perhaps the losses I eventually make will allow for some offsets of my BTC profits on my next tax return.
Anyway, I’m wondering if I’m not doing backtesting right. More likely I’m not doing my strategy right. Perhaps I should be including stops, and use backtesting to determine what the best level for a stop is. But given that future behaviour is completely unrelated to past behaviour in nearly everything I trade, is this even a worthwhile exercise?
Crypto is a wild space. Nearly everything is speculative. My overall hope is that as the crypto space matures it will move closer to more traditional asset classes, and approaches that have worked for, say, equities, will eventually start working for crypto as well. Perhaps I should stick with the most mature crypto projects. In the interests of diversity I’m trading a lot of coins that I hadn’t heard of before this current iteration of my strategy. There are a lot of coins available on Binance Cross Margin that weren’t there a year ago. Looks like that might be a mistake.