| Title | Evaluating Trade Side Classification Algorithms Using Intraday Data from the Warsaw Stock Exchange |
| Authors | Olbryś, Joanna and Mursztyn, Michał |
| Year | 2018 |
| Volume | Archives of Data Science, Series A 4(1) / 2018 |
| Abstract | According to the literature, to measure both market liquidity and dimensions of market liquidity based on intraday data, it is essential to recognize the side initiating a transaction. Although the Warsaw Stock Exchange (WSE) is an order-driven market with an electronic order book, information of the order book database is not publicly available. Trade side classification algorithms enable us to assign the side that initiates a transaction and to distinguish between the so-called buyer- and seller-initiated trades. The aim of this paper is to evaluate several trade side classification procedures using high frequency intraday data for the WSE. The whole sample covers the period from January 3, 2005 to December 30, 2016, and it includes the Global Financial Crisis. Selected trade side classification algorithms are implemented, tested and compared with each other. Moreover, the robustness analysis of empirical results is provided. The empirical experiments show that the Lee and Ready (1991) algorithm performs better than other procedures on the WSE. |