文献类型：期刊文献

英文题名：Learning representation of stock traders and immediate price impacts

作者：Xie, Wen-Jie[1,2];Li, Mu-Yao[1];Zhou, Wei-Xing[1,2,3]

机构：[1]East China Univ Sci & Technol, Sch Business, 130 Meilong Rd,POB 114, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Res Ctr Econophys, Shanghai 200237, Peoples R China;[3]East China Univ Sci & Technol, Dept Math, Shanghai 200237, Peoples R China

年份：2021

卷号：48

外文期刊名：EMERGING MARKETS REVIEW

收录：;WOS:【SSCI(收录号:WOS:000693244900002)】；

基金：This work was supported by the National Natural Science Foundation of China (Grant No. U1811462) , the Shanghai Outstanding Academic Leaders Plan, and the Fundamental Research Funds for the Central Universities.

语种：英文

外文关键词：Machine learning; Network embedding; Trading network; Price impact

摘要：We use 239-day trading-level data for a stock on the Shanghai Stock Exchange, including about 440,000 traders and 1.77 million trading relationships, to study the representation of traders in a trading network using the network representation learning method, and to identify different traders' local outlier factor (LOF). Based on the local outlier factors, traders are divided into two categories: novel and normal. The novel traders' orders have smaller immediate price impact. Our method can be used to characterize and discover the behavior of medium-scale trading networks and provide certain decision support for market investors and regulators.