not OP. I have a competing product with an ad-hoc algorithm that I 100% believe is better than FSRS (tested it for months or real practice)

But what you ask is not feasible, neither I nor OP have 700 millions of reviews to stack up against FSRS.

I have my own experience and a bunch of simulations, and if FSRS were better I would have switched to it.

The reason in my case btw is that FSRS is generic, mine is tailor made for languages - big difference.