استخراج تامینی و آربیتراژ بازار ارز تایوان

The foreign exchange market is one of the biggest markets in the global financial capital market. With current trends toward financial capital globalization, it is becoming more important to understand the hedge and arbitrage of foreign exchange markets. Thus, this study implements association rules as a data mining approach to explore the associations among 19 different pairs of foreign exchange rates. Transaction data, such as foreign exchange rates, were collected to construct a database; the Apriori algorithm was then used to generate the association rules. By doing so, this study proposes several possible portfolio alternatives in the Taiwan foreign exchange market, including foreign exchange hedge and arbitrage under different circumstances.

According to the 2009 survey of the Bank for International Settlements (BIS), the average daily turnover of the global foreign exchange market is $4.3 trillion. According to the Central Bank of the Republic of China (Taiwan), the average daily turnover of the foreign exchange market in Taiwan is $29.23 billion. The foreign exchange market has the largest trading volume of any single market in the world. Operating 24-h, the international financial market has a pivotal position. The influence of the Asian financial crisis in 1997 on the international financial market shows that a large number of withdrawals of international capital can enable a single country, or can even be a serious threat to a region as a whole. In financial and market globalization, with trends toward liberalization, traders, investors, speculators, bankers and other participants in the foreign exchange market make repeated daily transactions, such as arbitrage and hedging actions, so as to activate countries’ stock markets and capital flows. Through globalization in finance and trade, all countries and firms are increasing their dependence on foreign trade. This kind of trade relationship leads to a dependent response in the foreign exchange market. Thus, integration of hedging, arbitrage, and portfolio analysis in financial capital markets in terms of investment and risk management study has becomes a critical research issue (Ghosh et al., 2010 and Montana et al., 2009). In addition, there are three degrees of financial capital market efficiency. The first degree is the strong form of the efficient market hypothesis, which states that all information that is knowable is immediately factored into the market’s price for security. If this is true, then all price predictors are definitely wasting their time, even if they have access to private information. The second degree is the semi-strong form of the efficient market hypothesis, in which all public information is considered to possess private information, which can be used for profit. The third degree is the weak form, which holds only that any information gained from examining a security’s past trading history is reflected in price. Indeed, past trading history is public information, implying that the weak form is a specialization of the semi-strong form, which itself is a specialization of the strong form of the efficient market hypothesis. Due to the different degrees of market efficiency, academic researchers investigate the efficient market hypothesis by exploring unknown and valuable knowledge from historical data, using techniques such as data mining. Enke and Thawornwong (2005) introduced an information gaining technique used in machine learning for data mining to evaluate the predictive relationships of numerous financial and economic variables. Neural network models for level estimation and classification are then examined for their ability to provide an effective forecast of future values. Boginski, Butenko, and Pardalos (2006) proposed a network representation of stock market data referred to as a market graph, which is constructed by calculating cross correlations between pairs of stocks based on opening price data over a certain period of time. Chun and Park (2005) proposed a learning technique, which extracts new case vectors using Dynamic Adaptive Ensemble CBR (DAE CBR). The main idea of DAE CBR is based on finding combinations of parameters and updating and applying an optimal CBR model to an application or domain area. These concepts are investigated against the backdrop of a practical application involving the prediction of a stock market index. In addition, Rapach and Wohar (2006) implemented an analysis of in-sample and out-of-sample tests of stock return predictability in an effort to better understand the nature of the empirical evidence in return predictability. Their study finds that certain financial variables display significant in-sample and out-of sample predictive ability with respect to stock returns. Overall, most studies consider stock market analysis as a time series problem, and there have been few studies have used stock market efficiency to explore the possible cause-and-effect relationships among different stock categories or the influence of outside factors (Liao, Ho, & Lin, 2008). On the other hand, Montana et al. proposed a concept of statistical arbitrage, an investment strategy that exploits patterns detected in financial data streams. They demonstrate that flexible least squares (FLS) are algebraically equivalent to the well-known Kalman filter equations, and take advantage of this equivalence to gain a better understanding of FLS and suggest a more efficient algorithm. Their study presented promising experimental results obtained from a FLS-based algorithmic trading system for the S&P 500 Futures Index are reported (Montana et al., 2009). Accordingly, this study investigates the research issues related to the hedging and arbitrage of the Taiwan exchange market. They issues discussed here include: (1) from the October 1, 2008 to September 30, 2009 transactions in the Taiwan foreign exchange market were predominately in NT dollars. The foreign currency exchange rate between the 19 files changed due to their relevance and mutual influence. We go on to explore the various types of foreign currency, examining whether the ups and downs are linked or whether the order of interaction, that is, the relationship between the ups and downs is relevant. We also assess the influence of the rising effect losing streaks on compensatory growth. (2) To explore the links with the mining out of the actual foreign exchange rules and make a comparative analysis of market trends. (3) To examine how each of the ups and downs of the currency linked relationship between the arbitrage and hedging of operations are applied to the proposed business and corporate investment to avoid exchange rate risk and profit objectives. The rest of this study is organized as follows. In Section 2, we present the background of foreign exchange market management and the stock market in Taiwan. Section 3 describes the methodology, including the research framework, data sources, and database design. Section 4 presents the data mining approach, association rules, and data mining tool – SPSS Clementine, and discusses research findings. Section 5 illustrates the data mining results and Section 6 describes research findings and managerial implications. Finally, Section 7 presents a brief conclusion.

This study considers that foreign exchange rates have strong associations with both inside and outside factors. Some foreign exchange rates are rising or dropping together at the same time. For individual or institutional investors, finding indications for the trends of foreign exchange market associations is a valuable task. Data mining of foreign exchange market analysis and interpretation of the arbitrage and hedging of the data mining results gives new insights into possible associations in financial capital markets. In this study, we use a data mining approach, the Apriori algorithm, to generate association rules. By doing so, this study finds that different possible portfolios of foreign exchange currencies can be implemented in the Taiwan financial capital market. Thus, this case study of implementing data mining approaches and integrating them into financial investment research in Taiwan is an example for future research and implementation.