> Do you run it with good volumes or are these returns “as if”?

This trades the S&P 500. The SPY ETF along trades 21 billion dollars a day of volume. He'd probably need to trade a billion dollars to impact it.

Ofc, but as far as I understand algotrading, you don’t need to move a market for other bots to abuse your scheme eventually. Works on real non-toy money since 2022 and works on your napkin simulation since 2022 is a huge difference.

Depending on the market, that threshold can be crazy low. Many smaller brokers make most of their profit by playing against their "customers". Small players can't use the big brokers, and even if they become big players, this just attracts other big players to use their bots against them.

It's a dark forest out there.

Source: I knew several people starting out with a few hundred thousand, "doing really well", and then soon as they crossed some magic number like one million dollars they suddenly started getting front-run on every trade until they gave up. Two of them spent years trying to "fix" their algorithm until they finally figured out what was happening to them.

This basically confirms my concern. It’s known that algo doesn’t live long on sensible amounts. It’s a never-ending churn between bots who don’t even take you personally. It’s as simple as the N+1 guy learning (ml or human ideas) on the whole market that N is a part of and stealing profits from all n <= N by design.

If OP managed to run it live since 2022, I’d be very surprised and glad for them. If not, condolences for the time lost on napkin profitability.