• Stars
    star
    221
  • Rank 179,773 (Top 4 %)
  • Language
    Jupyter Notebook
  • License
    MIT License
  • Created over 4 years ago
  • Updated about 2 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

High Frequency Market Making

Note: Due to high number of requests I am in the process of writing some mathemagical notes which seek to explain what is going on here and what kind of models the solvers are supposed to represent. Sit tight!

HFT

This repository contains semi random collection of "High Frequency Market Making" algorithms created using stochastic optimal control. Resulting Dynamic Programming Equations are solved using simple Euler finite difference scheme.

AS++

  • Avellaneda Stoikov inspired model
  • Terminal inventory penalty
  • Running inventory penalty

ASAS

  • Avellaneda Stoikov inspired model
  • Terminal inventory penalty
  • Running inventory penalty
  • Factors adverse selection into the optimal distances

AS+++

  • Avellaneda Stoikov inspired model
  • Terminal inventory penalty
  • Running inventory penalty
  • Hedging areas using QVI conditions over value function
  • Factors liquidity rebate into the optimal distances

ASMP

  • Avellaneda Stoikov inspired model
  • Incorporates Stoikov's Micro-Price model into the optimal decision to either be at the best bid or offer.