In nature, the balance of males and females is maintained by natural selection acting on parents. As Sir Ronald Fisher brilliantly pointed out in 1930, a surplus of one sex will be redressed by selection in favour of rearing the other sex, up to the point where it is no longer the minority. It isn’t quite as simple as that. You have to take into account the relative economic costs of rearing one sex rather than the other. If, say, it costs twice as much to rear a son to maturity as a daughter (e.g. because males are bigger than females), the true choice facing a parent is not “Shall I rear a son or a daughter?” but “Shall I rear a son or two daughters?”
So, Fisher concluded, what is equlibrated by natural selection is not the total numbers of sons and daughters born in the population, but the total parental expenditure on sons versus daughters. In practice, this usually amounts to an approximately equal ratio of males to females in the population at the end of the period of parental expenditure.
Note that the word ‘decision’ doesn’t mean conscious decision: we employ the usual ‘selfish gene’ metaphorical reasoning, in which natural selection favours genes that produce behaviour ‘as if’ decisions are being made.