Online Learning of Informed Market Making

Abstract

Many economic markets, including most major stock exchanges, employ market-makers to aid in the transactions and provide a better quality market. This Study is aimed to establish an analytical foundation for electronic market making strategy, by giving a probabilistic interpretation to the Bid-Ask spread. The suggested strategy will be optimized with on-line learning from the high frequency data of the TASE (Tel Aviv Stock Exchange) order book. Based on this foundation, we wish to create an automated securities dealer that will perform the task of providing liquidity to the markets efficiently, and with low downturn risk. We compare the expected performance of the automated dealer with several bench mark measures of Market liquidity such as those presented in Roll (1984) and Glosten & Milgrom (1985).