Online learning of informed market-making

Many economic markets, including most major stock exchanges, employ market-makers to aid in the transactions and provide a better quality market. This study aims 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 benchmark measures of market liquidity such as those presented in Roll (1984) and Glosten & Milgrom (1985).

The main function of a security market is to provide a venue where buyers and sellers can transact. The efficiency of the market is measured by its liquidity, which is defined as ability to execute transactions quickly without causing significant movements in price. For this reason exactly, most stock exchanges over the world have dealers. The role of a dealer is to provide liquidity on the exchange by quoting bid and ask prices at which he is willing to buy and sell a specific quantity of assets. Traditionally, this role has been filled by market-makers or specialist firms. In recent years, with the growth of electronic exchanges, anyone willing to submit limit orders in the system can effectively play the role of a dealer. In our paper, we study the submission strategies of bid and ask quotes in such a limit order book.

References:

Richard Roll, A Simple Implicit Measure of the Effective Bid-Ask Spread in an Efficient Market, 34 Journal of Finance 1127 (1984)

Lawrence R. Glosten and Paul Milgrom, Bid, ask and transaction prices in a specialist market with heterogeneously informed traders, 14 Journal of Financial
Economics 71-100 (1985)