Pattern recognition in trading behaviors before stock price jumps: new method based on multivariate time series classification

This paper extends the work of Boudt and Pertitjean(2014) and investigates the trading patterns before price jumps in the stock market based on a new multivariate time classification technique. Different from Boudt and Pertitjean(2014), our analyzing scheme can explore the "time-series information" embedded in the trading-related attributes and provides a set of jump indicators for abnormal pattern recognition. In addition to the commonly used liquidity measures, our analysis also involves a set of technical indicators to describe the micro-trading behaviors. An empirical study is conducted on the level-2 data of the constituent stocks of China Security Index 300. It is found that among all the candidate attributes, several volume and volatility-related attributes exhibit the most significant abnormality before price jumps. Though some of the abnormalities start just shortly before the occurrence of the jumps, some start much earlier. We also find that most of our attributes have low mutual dependencies with each other from the perspective of time-series analysis, which allows various perspectives to study the market trading behaviors. To this end, our experiment provides a set of jump indicators that can effectively detect the stocks with extremely abnormal trading behaviors before price jumps. More importantly, our study offers a new framework and potential useful directions for trading-related pattern recognition problem using the time series classification techniques.