投資策略模型有千百種，背後的運算邏輯也大不相同，若是運用不同的演算法進行建模，預測能力必定也不相同。投資人若對標的物僅使用一種策略模型進行預測，其預測力有其上限，考量的因素也無法全面。再進場之後獲利時間點之選擇亦無法精準預測。此時如何能夠同時掌握不同策略模型間的特性和優點，以及找到一套最適當的出場時機規則，為本研究欲解決之問題。
欲解決上述之問題，本研究欲建構出一個即時的投資交易平台，透過多種不同演算法的策略模型，以及同時使用不同時間粒度的歷史資料建出之模型相互參考並輔以權重，使得進場信號的產生不再是僅依靠單一策略，進而提升預測的準確度。此部分將運用Apache Storm的分散式架構來進行實作，從接收市場每秒鐘的即時報價、運算完該秒鐘上千種的市場狀態、再到多個策略間彼此產出信號，僅需要花費毫秒級別的時間即可完成，並轉交給券商下單。而搓合的結果則是透過Kafka的訊息傳遞機制來實現，系統以訂單的狀態來判定最佳的出場時機。

1. Fan, A and Palaniswami, M. (2001), Stock selection using support vector machines, Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on.
2. Qinghua Wen, Zehong Yang, Yixu Song and Peifa Jia (2009) , Automatic stock decision support system based on box theory and SVM algorithm, Expert Systems with Applications Volume 37, Issue 2, March 2010, Pages 1015–1022.
3. Shom Prasad Das and Sudarsan Padhy (2012), International Journal of Computer Applications (0975 – 8887) Volume 41– No.3, March 2012.
4. lebeling Kaastra and Milton Boyd (1996), Designing a neural network for forecasting financial and economic time series, Neurocomputing Volume 10, Issue 3, April 1996, Pages 215–236, Financial Applications, Part II.
5. Wensheng Dai, Jui-Yu Wu, Chi-Je Lu (2012), Combining nonlinear independent component analysis and neural network for the prediction of Asian stock market indexes, Expert Systems with Applications Volume 39, Issue 4, March 2012, Pages 4444–4452.
6. Muh-Cherng Wu, Sheng-Yu Lin and Chia-Hsin Lin (2006), An effective application of decision tree to stock trading, Expert Systems with Applications
7. Volume 31, Issue 2, August 2006, Pages 270–274.
8. Long Wang and Shu-Hui Chan (2006), Stock market trading rule discovery using two-layer bias decision tree, Expert Systems with Applications Volume 30, Issue 4, May 2006, Pages 605–611.