Stocks choice?

[jmg17]

There is probably an error in the choice of stocks because the choice is made on stocks of which we know the good behavior
for the period 2015/01 2020/01 the proposed portfolio (AAPL, AMD, AMZN, FB, MSFT, NFLX, NVDA, TSLA) with equal weights and buy and hold has a performance of approximately 1000% !!.
Eiten GA returns 450%. Not so good.
If you randomly choose stocks from 2015, the result is not good.

[silvavn]

@jmg17 portfolio optimization is different from picking stocks. The GA method attributes optimized random weights to the stocks, it does not, however, guarantee to be optimal, since it is a stochastic method. But yes you are correct, there is room for improvement in the strategies currently implemented.

[tradytics]

@jmg17 - thank you for your comments. Did you try randomly choosing stocks from 2015 and run the strategies?

Also, when you are using this to invest real money, you usually don't pick random stocks. Although the choice of stocks in the experiments was somewhat unfair maybe, you'll always pick stocks that you have high confidence in. Therefore, the fact that something doesn't work on random set of stocks doesn't hold any weight.

Happy to discuss more.