1 code implementation • 24 Nov 2022 • Lorenzo Lucchese, Mikko Pakkanen, Almut Veraart
The performance of the deep learning models is strongly dependent on the choice of order book representation, and in this respect, the volume representation appears to have multiple practical advantages.
no code implementations • 2 Oct 2021 • Claudio Bellani, Damiano Brigo, Mikko Pakkanen, Leandro Sanchez-Betancourt
We present a measurement of price impact in order-driven markets that does not require averages across executions or scenarios.
2 code implementations • 17 Feb 2020 • Swapnil Mishra, Seth Flaxman, Tresnia Berah, Harrison Zhu, Mikko Pakkanen, Samir Bhatt
We show that our framework can accurately learn expressive function classes such as Gaussian processes, but also properties of functions to enable statistical inference (such as the integral of a log Gaussian process).