Della Penna, NicolasReid, Mark2019-11-252019-11-25http://hdl.handle.net/1885/186624We propose a flexible framework for profit-seeking market making by combining cost function based automated market makers with bandit learning algorithms. The key idea is to consider each parametrisation of the cost function as a bandit arm, and the minimum expected profits from trades executed during a period as the rewards. This allows for the creation of market makers that can adjust liquidity and bid-asks spreads dynamically to maximise profits.application/pdfen-AU© 2011 The Author(s)https://creativecommons.org/licenses/by-nc-sa/3.0/20112019-05-19Attribution-NonCommercial-ShareAlike 3.0 Unported (CC BY-NC-SA 3.0)