Authors : Wanli Chen and Zhe Qin
Abstract: In stock markets, the performance of traditional technology-based investment methods is limited because they only take into account single-dimensional event factors. The study shows how the integration of multi-dimensional stock market dynamics can improve performance and proposes a three-layer integrated investment decision-support framework. In the framework, we emphasize on one key dynamics that previous studies have neglected: unique trends of stocks-the patterns which only relate to individual stocks themselves. We adopted a Domain Knowledge-dependent AutoSplit method to study the dynamics and investigate its usage. Our experiments showed that this key dynamics plays an important role in investment decision making and it is an essential part of the framework. The integrated investment framework with incorporating this key dynamics is promising and our experimental results showed that it outperformed single-dimensional traditional methods and benchmark indices.
Wanli Chen and Zhe Qin , 2006. Identification of Unique Trend Dynamics in An Integrated Investment Decision-Support Framework. Asian Journal of Information Technology, 5: 742-749.