Showing papers by "An-Pin Chen published in 2007"

Constructing a dynamic stock portfolio decision-making assistance model: using the Taiwan 50 Index constituents as an example

Abstract: There are several decisions in investment management process. Security selection is the most time-consuming stage. Tatical allocation is in order to take advantage of market opportunities based on short-term prediction (Amenc and Le Sourd in Portfolio theory and performance analysis. Wiley, 2003). Although it is difficult to keep track of the fluctuations of volatile financial markets, the capacity of artificial intelligence to perform spatial search and obtain feasible solutions has led to its recent widespread adoption in the resolution of financial problems. Classifier systems possess a dynamic learning mechanism, they can be used to constantly explore environmental conditions, and immediately provide appropriate decisions via self-aware learning. This study consequently employs a classifier system in conjunction with real number encoding to investigate how to obtain optimal stock portfolio based on investor adjustment cycle. We examine the constituents of the TSEC Taiwan 50 Index taking moving average (MA), stochastic indicators (KD), moving average convergence divergence (MACD), relative strength index (RSI) and Williams %R (WMS %R) as input factors, adopting investor-determined adjustment cycle to allocate capital, and then constructing stock portfolio. We have conducted empirical testing using weekly and monthly adjustment cycle; the results revealed that this study’s decision-making assistance model yields average annual interest rate of 49.35%, which is significantly better than the −6.59% of a random purchase model. This research indicates that a classifier system can effectively monitor market fluctuations and help investors obtain relatively optimal returns. The assistance model proposed in this study thus can provide really helpful decision-making information to investors.

Designing a Dynamic E-learning Project Performance Evaluation Framework

Abstract: A proper e-learning environment is one of the most important knowledge management tools in today's organizations. However, many of them lack a universal evaluation process to verify their e-learning project's performance. In an attempt to solve this problem, this study bases on Kirkpatrick's model and combines the balanced scorecard and the option pricing approach to provide an easy to use, easy to understand and easy to analysis framework for e-learning project's performance evaluations.

Applying Extensible Classifier System to Inter-market Arbitrage with High-Frequency Financial Data

Abstract: The most popular arbitrage opportunities detecting methodology is derived from the cost of carry model. Recently, many researches were intent to enhance the accuracy of these arbitrage models using econometrics approach. However, the market behavior is still hard to be known well, especially when inter-market spread trade with intra day one minute tick data. This research is aimed at inter-market arbitrage with high frequency data, and two futures indexes are used for empirical study, including Taiwan Stock Index Futures of Taiwan futures exchange (TAIFEX) and MSCI Taiwan Index Futures of Singapore Exchange Limited (SGX). Moreover, the price of index futures will get close to that of spot products when the futures contract is due. Founded on such property, the spread ratio and the different due days of TAIFEX and SGX, we finally build up an extended classifier based arbitrage system which can gauge the timing of index stock deals.

Modeling e-Learning System Performance Evaluation with Agent-Based Approach

Abstract: Rapidly evolving information technology has dramatically changed the knowledge dissemination process. A proper e-learning environment is one of the most important knowledge tools in modern organizations. However, many of them lack a generic evaluation process to verify performance. In an attempt to solve this problem, this study propose an agent-based model which compose learning model, balanced scorecard and the option pricing approach to provide an dynamic, flexible framework for e-learning project's performance evaluations.

Using computational methodology to price European options with actual payoff distributions

Abstract: Most option pricing methods use mathematical distributions to approximate underlying asset behavior. However, pure mathematical distribution approaches have difficulty approximating the real distribution. This study first introduces an innovative computational method for pricing European options based on the real payoff distribution of the underlying asset. This computational approach can also be applied to applications related to expected value that require real distributions rather than mathematical distributions. This study makes the following contributions: (a) solving the risk neutral issue related to price options with real payoff distributions; (b) proposing a simple method for adjusting standard deviation based on the need to apply short term volatility to real world applications; (c) demonstrating an option pricing algorithm that is easy to apply to cross field applications.

Hybrid Intelligent Trading Approach XCS Neural Network Model for Taiwan Stock Index Trend Forecasting

Abstract: Econometricians build precise hypotheses in advance when they use econometric models to discuss changing stock market trends. However, baffled by these unreasonable hypotheses, economics generally cannot effectively explain real stock market behaviors using mathematical models. Therefore, this study attempts to use genetic theories to produce a rule base that can be adapted to stock market behaviors, and then re-learns it to refine those rules, hopefully discovering knowledge hidden in the stock market. Artificial intelligence models recently have been frequently applied in financial analysis. Compared with econometric models, which require numerous hypotheses and suffer various other limitations, artificial intelligence models are more flexible, able to solve any nonlinear problems, and more suitable for analyzing dynamic environments such as stock markets. This study combines two artificial intelligence technologies: the extended classifier system and backpropagation neural network to establish a XCS-neural-network based trading system, and this system is then used to identify environmental patterns and predict the values of the test set. Experiments reveal that all test data in this study have accuracy rates exceeding 50%. Therefore, this study confidently concludes that the proposed system can help investors make more precise investment decisions.

Exchange Rates Forecasting Using a Hybrid Fuzzy and Neural Network Model

Abstract: Artificial neural networks (ANNs) are promising approaches for financial time series prediction and have been widely applied to handle finance problems because of its nonlinear structures. However, ANNs have some limitations in evaluating the output nodes as a result of single-point values. This study proposed a hybrid model, called fuzzy BPN, consisting of backpropagation neural network (BPN) and fuzzy membership function for taking advantage of nonlinear features and interval values instead of the shortcoming of single-point estimation. In addition, the experimental processing can demonstrate the feasibility of applying the hybrid model-fuzzy BPN and the empirical results show that fuzzy BPN provides a useful alternative to exchange rate forecasting

A collaboration environment for R&D project

Abstract: The research question here is "how to effectively integrate the R&D experts and software developers to realize an effective R&D project collaboration software?" This research conducted a case study on the deployment of an integrated development methodology in a world-class semiconductor manufacture company. From the case study, the integrated methodology, Development Collaboration Diamond Model (DCDM), was designed, implemented and obtained the dramatic performance.