[1M2] [General Session] 13. AI Application

[1M2-04] Algorithmic Detection of Quote Spoofing in Stock Exchange Market Using Probability Density Ratio Estimation

〇Kenichi Nakahara¹, Fumiya Shimada¹, Kunihiro Miyazaki¹, Masayuki Sekine¹, Shouhei Ohsawa¹, Makoto Ohshima², Yutaka Matsuo¹ (1. The University of Tokyo, 2. DSB Co., Ltd.)

Keywords:Anomaly Detection, Importance Fitting, Financial Market

We propose a model to quantitatively estimate quote spoofing in stock exchange markets without any answer labels, for the sake of more efficient and thorough inspection. In our model, density ratio estimation is used to extract unusual trading activities in unsupervised manner. Using market data at Tokyo Exchange and judges by experts, we validate the model and the result indicates that about 50% of half-day grouped trading histories can be ignored of manual inspection with 80% of frauds in the rest half of the dataset.