I spent a week trading based on an AI’s signals, so you don’t have to. Here are the results.

AI is taking over many jobs, starting from cashiers all the way to doctors. I wanted to see if AI could replace traders by running a small (and maybe a costly) experiment.

Rules are simple. For the next week, I’ll open a long/short Bitcoin position based on an AI twitter bot forecasts. Every position should be opened at 00:00 UTC and closed at 23:59 UTC.

Our start balance is $1000. And we won’t use leverage in our trades.

Day 1: A great start

We opened a short position at $29.5K and closed it at $29K. We ended up with a profit of $17. This brings our final balance to $1017.

Day 2: Sometimes it happens

We didn’t open any positions since the AI bot’s forecast seemed neutral.

Day 3: Two wins in a row?

We opened a long position at $28.6K and closed it at $29K. We ended up with a profit of $14. This brings our final balance to $1031.

Day 4: THREE wins in a row?

We opened a long position at $29K and closed it at $30.3K. We ended up with a profit of $46. This brings our final balance to $1077.

Day 5: I knew it’d happen

We opened a short position at $29.5K and closed it at $31.8K. We ended up with a loss of $84. This brings our final balance to $993.

Day 6

We didn’t open any positions since the AI bot’s forecast seemed neutral.

Day 7: Will we recover?

We opened a long position at $31.8K and closed it at $29.7K. We ended up with a loss of $66. This brings our final balance to $927.

Summary

Of course, five trades aren’t enough to evaluate any trading strategy. The bot seemed to do well initially, but then the market started crashing.

• We won three trades and lost two. Our win rate is 60%.
• We won a total of $77 and lost $150. Finishing with a total loss of $73.

This small experiment shows that the crypto market is genuinely unpredictable. Sometimes your predictions turn out right, and most of the time, they don’t.