Agree mostly, caveat though that some pricing models indeed are better than others at capturing the true distributional properties. The French quant derivatives guilt has carved itself out a nice edge by running their own customized pricing models that I firmly believe capture risk (the first derivatives and higher order ones) better than classic pricing models. I have seen it way too much over the many years to resort the out performance to mere chance.
My issue with the differencing method is that anytime you take a difference, you add 6dB of noise at the Nyquist frequency. You can see this in the differenced data versus the original data. The differenced data may be stationary, but is also much noisier.
I find close to zero value in differencing financial time series. Just mentioned it as it is one way to get to a stationary series, which financial asset price series are not.
all this does not matter can you make money or not? are you making money or not? if you cannot find something else. saying i am making money because of luck or gambling is foolish
when market is driven by money flows, by buyers and sellers, to say market is random is to say that buyers and sellers act randomly.
market is not random all the time. "if the market was random i would be a bum with a tin cup"Warren Buffet