In stock markets, the performance of traditional technology-based investment methods is limited because such methods only take into account single-dimensional event factors. The study shows how the integration of multi-dimensional event factors can improve performance. We propose a novel three-layer integrated framework composed of Analysis, Synthesis and Investment Decision Support. At the first layer, multi-dimensional stock market structures are identified, in which we emphasize two key aspects that previous studies have neglected: unique trends of stocks-the patterns which relate only to individual stocks themselves and a two-way reflexivity relationship of investors? decisions and market reactions. At the second layer, multi-dimensional pattern components are synthesized to reflect real (and potential) market situations. At the third layer, a prototype integrates the functions of first two layers for investment decision support. The framework covers multi-dimensions of market structures and incorporates the concepts and advantages of traditional investment methods. The framework is promising, because experimental results indicated that it outperformed market baselines and single-dimensional conventional methods.
展开▼
