Rant mode on. I don’t care about your big data. Increasingly I care about small data. If you can talk sense having very little data then you have a chance when more data arrive. The converse is not true

We saw screens go wide or empty in March. How did your cutesy machine learning algo do then?

Here’s a vol quant question worth thinking about. I give you the vols at 40 delta put and 40 delta call. Nothing else. Build me a smile that’s arb free.

I’ll give you those for say Feb and June. So you have 4 vol points. Build me an entire arb free surface you’d be prepared to use in anger. Price me an April risk reversal, no tears.

These are vital risk management questions yet time is wasted on fine tuning a stochastic local vol model. GLWT. We are awash in data, and every cheap ass Bloomberg-lite middle man is charging for it

And you’re paying because you think you need more. You don’t. You need to be able to cope with less. Then anything the market gives you is a bonus

Your complete reliance on your calibrated local vol model is the cause of your exo book loss. Your enormous factset data is the reason your quant strategy melted.

Data isn’t edge. It’s just data. If everyone else has it, how about your edge can be not having it. Or not having it yet.

Every risk factor you call stochastic and correlate to other stuff is something you’ve given up on actually understanding. Here’s looking at you, French exo trader number 3475981

Oh that doesn’t work let’s add jumps

Ok let’s add vol jumps

Ok now let’s correlate the spot jumps and the vol jumps

And you still can’t sensibly say where the vol surface will be if we gap 2 std devs down

Am getting worried this is turning Talebian. If I start lifting weights you’re allowed to shoot me ok

What this is, I guess, is a plea for domain expertise and understanding to be valued. It’s a request for more fundamental research. Less AI garbage.

OK rant mode off. Time to really rebuild. There’s huge opportunities out there