Dismal Realism Factor (RF) - don't trade systems with less than 80% RF - not a honest system. Also uses limit orders - will get filled on all losers, but rarely on winners because the fills not only depends on FIFO order but also on the size of the order; so that the actual equity curve would look a downward 45 degree slope, not an upward one.
Even if one converts limit orders to market orders, optimal dynamic asset-allocation policy is generally unattainable due to transaction costs and other market frictions (slippage), but can be approximated with just a few options given that only a few trades are required to establish the portfolio and there are few costs to bear thereafter.
An even more compelling motivation for the optimal buy-and-hold portfolio is the presence of taxes. For taxable investors, the Certainty Equivalent (CE) is reduced by the present value of the sequence of capital gains taxes that are generated by an optimal dynamic asset-allocation strategy. In contrast, all of the capital gains taxes are deferred until a future point in time in a buy-and-hold portfolio. Therefore, the economic value of predictability is likely to be even lower for taxable investors, and the optimal buy-and-hold portfolio that much more attractive. The main challenge is tractability and computational complexity.
Deriving optimal buy-and-hold strategies to approximate other than dollar-cost averaging strategies or other popular dynamic investment strategies - strategies that need not be based on expected utility maximization might be of considerably lesser interest.
We have to examine the payoff structure of the portfolio and its sensitivities to various market factors and economic shocks.
I think auto trading is advanced AI but on one condition: provided you begin by reaching independent conclusions. Then you must accept the responsibility of implementing your own conclusions in practice; using auto- or manual trading, i.e., you must pave your own way. You must be self-reliant in the mental world and in the physical world.