When you're in the financial industry, everything is about prediction. So if you could find like time-lagged correlations in finance, those things are as good as money. But because everyone's trying to do it simultaneously, you get these really small correlations and so you're just in this constant cloud of data. It says basically as non-stationary or I think in machine learning they talk about more of like out of sample distribution. And then in 2019, I moved over to Lyft and have been since there ever since doing causal inference and causal forecasting,. Trying to help them manage that really complicated market that I've come to love and hate.