本篇論文主要探討台灣期貨市場於2005年至2008年的快速抽單(Fleeting orders)現象。文章將市場交易者區分為機構法人、散戶、自營商以及外資共四類族群，研究抽單背後的動機是否與各族群中交易者的下單積極程度、追價動作，或是降低成交成本有關。實證結果顯示，機構法人在快速抽單動作上無顯著動機；在散戶部分，僅部分散戶具有能力進行快速抽單，而其主要動機是為了降低交易成本。自營商的進場動機，主要是以造市為考量，因此測試市場上是否存在更激進的交易對手單是快速抽單的原因之一。此外，自營商亦會因要降低成交成本而進行快速抽單的動作。由於外資的主要策略是使用波段操作獲取大額利潤，無顯著證據證明外資進行快速抽單的動機是涵蓋於上述三種假設。 本文亦透過實證分析，探討快速抽單與合約報酬的關係，並以研究觀察有較高的快速抽單率是否會帶來較佳報酬，實證結果顯示各族群皆無顯著正相關，但散戶有顯著負相關。四類族群各自有不同的交易型態，故不能將他們概一而論，本篇論文的貢獻即是透過快速抽單，證明四個交易族群在程式交易上，具有不同的策略方向以及對於市場有不同的熟悉程度。 / This paper focuses on the phenomenon of fleeting orders in Taiwan’s futures markets from 2005 to 2008. Traders who in the markets will be divided into local institutional investors, individual, Dealer, and foreign institutional investors. Our study will find the motivation behind fleeting orders under the three hypotheses: attractive, chasing, and the cost-of-immediacy. The empirical results show that local institutional investors have no significant motivation. Only part of individual investors have the ability to use fleeting orders, and their main motivation is to reduce transaction costs. Dealers act as a market maker, so the main motivation for dealers is to raise liquidity. So to test whether a more aggressive limit orders exists in the market is one of the reasons for them to submit fleeting orders. In addition, dealers will also cancel limit orders in order to reduce the transaction costs. Because the main strategy for foreign institutional investors is to obtain a large profit during a period, they have no significant evidence to explain any motivation under the three assumptions. This article also analysis the relationship between fleeting orders and performance, and investigate whether the high fleeting ratio could bring much better profits. The empirical result show that all of four type investors have no significant positive correlation of fleeting orders and performance, but individual investors have significant negative correlation of fleeting orders and performance. Each of four type investors has different trading patterns, so that we should treat them case by case. The contribution of this paper is to prove that the four type investors have different strategies when they use trading program, and they also have different experience in Taiwan’s futures markets.

本研究應用雲端分散式的架構來建置與佈署一個處理大量使用者交易需求的高頻交易投資策略服務平台，此平台有以下特色： 1. 系統後端採用雲端SOA架構，將整個龐大的交易系統切割佈署到雲端叢集之上，並提供單一的Façade介面供外部使用者呼叫；系統前端畫面的設計遵循Yahoo UI嚴格的MVC架構規範，並保證前端的View與Model與後端的資料達成同步。 2. 不斷接收來自外部的即時報價訊息，並產生海量的即時市場狀態資訊，包含多種技術分析指標、買賣規則…等，以供高頻交易的策略作為買賣的依據。 3. 利用Java Message Service將大量的即時市場狀態資訊快速、非同步的派送給分佈在雲端叢集各節點的系統模組，並採取Publisher-Subscriber的模式來維持分散後各系統模組之間的鬆散關係。 4. 多樣化的統計演算法模型可供使用者作為產生優良的個人化投資策略之依據。產生的新策略可馬上投入即時的模擬交易環境下監控與評估其策略績效。

在這份研究中，我們提出一個類分散式神經網路框架，此框架為高頻交易系統研究下之子專案。在系統中，我們透過資料探勘程序發掘財務時間序列中的模式，其中所採用的資料探勘演算法之一即為類神經網路。我們實作一個在分散式平台上訓練類神經網路的框架。我們採用Apache Spark來建立底層的運算叢集，因為它提供高效能的記憶體內運算（in-memory computing）。我們分析一些分散式後向傳導演算法（特別是用來預測財務時間序列的），加以調整，並將其用於我們的框架。我們提供了許多細部的選項，讓使用者在進行類神經網路建模時有很高的彈性。 / In this research, we introduce a distributed framework of artificial neural network (ANN) as a subproject under the research of a high-frequency trading (HFT) system. In the system, ANNs are used in the data mining process for identifying patterns in financial time series. We implement a framework for training ANNs on a distributed computing platform. We adopt Apache Spark to build the base computing cluster because it is capable of high performance in-memory computing. We investigate a number of distributed backpropagation algorithms and techniques, especially ones for time series prediction, and incorporate them into our framework with some modifications. With various options for the details, we provide the user with flexibility in neural network modeling.

金融市場是個變化莫測的環境，看似隨機，在隨機中卻隱藏著某些特性與關係。不論是自然現象中的氣象預測或是金融領域中對下一時刻價格的預測, 都有相似的複雜性。 時間序列的預測一直都是許多領域中重要的項目之一, 金融時間序列的預測也不例外。在本論文中我們針對金融時間序列的非線性與非穩態關係引入類神經網路(ANNs) 與集合經驗模態分解法(EEMD), 藉由ANNs處理非線性問題的能力與EEMD處理時間序列信號的優點，並進一步與傳統上使用於金融時間序列分析的自回歸滑動平均模型(ARMA)進行複合式的模型建構，引入燭型圖概念嘗試進行高頻下的台指期貨TAIEX交易。在不計交易成本的績效測試下本研究的高頻交易模型有突出的績效，證明以ANNs、EEMD方法與ARMA組成的混合式模型在高頻時間尺度交易下有相當的發展潛力，具有進一步發展的價值。在處理高頻時間尺度下所產生的大型數據方面，引入平行運算架構SPMD(single program, multiple data)以增進其處理大型資料下的運算效率。本研究亦透過分析高頻時間尺度的本質模態函數(IMFs)探討在高頻尺度下影響台指期貨價格的因素。 / Financial market is complex, unstable and non-linear system, it looks like have some principle but the principle usually have exception. The forecasting of time series always an issue in several field include finance. In this thesis we propose several version of hybrid models, they combine Ensemble Empirical Mode Decomposition (EEMD), Back-Propagation Neural Networks(BPNN) and ARMA model, try to improve the forecast performance of financial time series forecast. We also found the physical means or impact factors of IMFs under high-frequency time-scale. For processing the massive data generated by high-frequency time-scale, we pull in the concept of big data processing, adopt parallel computing method ”single program, multiple data (SPMD)” to construct the model improve the computing performance. As the result of backtesting, we prove the enhanced hybrid models we proposed outperform the standard EEMD-BPNN model and obtain a good performance. It shows adopt ANN, EEMD and ARMA in the hybrid model configure for high-frequency trading modeling is effective and it have the potential of development.