This paper proposes an intelligent trading system using support vector regression optimized by genetic algorithms (SVR-GA) and multilayer perceptron optimized with GA (MLP-GA). Experimental results show that both approaches outperform conventional trading systems without prediction and a recent fuzzy trading system in terms of final equity and maximum drawdown for Hong Kong Hang Seng stock index.

In various stock markets, there is a system called “circuit breakers” that interrupts dealing of stocks for a certain period when stock price changes greatly. In this paper, we consider the influence of the circuit breakers on a stock market using an agent-based artificial market simulator called “U-Mart”, by controlling the period of interruption and the criterion to invoke the circuit breaker...

Stock trading is an important decision-making problem that involves both stock selection and asset management. Though many promising results have been reported for predicting prices, selecting stocks, and managing assets using machine-learning techniques, considering all of them is challenging because of their complexity. In this paper, we present a new stock trading method that incorporates dy...

Consider the online regression problem where the dependence of the outcome yt on the signal xt changes with time. Standard regression techniques, like Ridge Regression, do not perform well in tasks of this type. We propose two methods to handle this problem: WeCKAAR, a simple modification of an existing regression technique, and KAARCh, an application of the Aggregating Algorithm. Empirical res...

The use of machine learning in the realm of finance is becoming much more prevalent as algorithmic trading catches on. Similarly, online social networking data becomes more valuable with new research in mining. The goal of this project is to take the next steps in these directions. Using different methods to interpret Twitter content, we hope to predict movement in the Dow Jones Industrial Aver...

Time-series data, which exhibit a low signal-to-noise ratio, non-stationarity, and non-linearity, are commonly seen in high-frequency stock trading, where the objective is to increase likelihood of profit by taking advantage tiny discrepancies prices trading on them quickly huge quantities. For this purpose, it essential apply method that capable fast accurate prediction from such time-series d...

Prior studies have documented that stock returns are abnormally high during the years following share repurchases and abnormally low following seasoned equity offerings, relative to various benchmarks of expected returns. While we confirm this evidence in the event data as of 2002, we do not find robust long-run abnormal returns following either stock repurchases or issuances after 2002. Instit...

Trading in stock market indices has gained unprecedented popularity in major ®nancial markets around the world. However, the prediction of stock price index is a very dif®cult problem because of the complexity of the stock market data. This study proposes stock trading model based on chaotic analysis and piecewise nonlinear model. The core component of the model is composed of four phases: The ...

Using a new hand-collected data set, this study examines the stock price manipulation in the Taiwan Stock Exchange (TSE). We examine the characteristics of the manipulated stocks, and their impacts on market quality. The results show that manipulated stocks tend to be small. The stock prices rise throughout the manipulation period, followed by a price reversal. The average cumulative abnormal r...