Fathoming empirical forecasting competitions’ winners

The M5 forecasting competition has provided strong empirical evidence that machine learning methods can outperform statistical methods: in essence, complex be more accurate than simple ones. Regardless, this result challenges the flagship led discipline for last four decades: keep sophisticatedly simple. Nevertheless, was a first, and we argue will not happen again. There been different winner each competition. This inevitably raises question: method win once (and should it expected to)? Furthermore, need to elaborate on perks of competing methods, what makes them winners?