Cluster Analysis of Liquidity Measures in a Stock Market Using High Frequency Data

Liquidity is one of the crucial factors in economy which reflects smooth operation of the markets. In a liquid market, traders are able to transact large quantities of security quickly with minimal trading cost and price impact. Many researchers have investigated the relationship between market liquidity and trading activity of a financial market. According to the existing literature, liquidity can measure different market characteristics such as trading time, tightness, depth, and resiliency. There is significant number of liquidity measures published in the literature. The main goal of this study is to use a hierarchical clustering algorithm to classify different liquidity measures. We examine the relationship between liquidity measures in order to detect commonality and idiosyncrasy among them. Then, we estimate the correlation among liquidity measures to quantify similarity between them and this quantity is used to develop a hierarchical clustering algorithm. At the end, we analyze the consistency in the structure of the clusters and we conclude that, clusters hold the same structure for almost 80% of the stocks in our sample. The data set that we are using for this study is NASDAQ High Frequency Trader (HFT) data. This data set contains trading and quoting activities of 26 HFT firms in 120 stocks on the Nasdaq exchange for various dates (in millisecond timestamp)