A Dea-cascor Model for High – Frequency Stock Trading: Computational Experiments in the U.s. Stock Market
نویسنده
چکیده
The paper presents results of computer-assisted portfolio management simulation based on using a DEACascor mathematical model. The model uses the Data Envelopment Analysis (DEA) ratio as a neuron with memory and combines it with Cascade Correlation Neural Network (Cascor) to forecast stock prices. The model is designed for using in high-frequency stock trading. It utilizes ability of DEA to concentrate multi-faceted information in one indicator scaled to the interval [0,1], a DEA efficiency index, and is aimed to compress market information. Cascor combines data of several consecutive periods using its flexible structure and generates a buy sell strategy. The paper presents results of the simulation of a 50-stock portfolio during a period of 60 consecutive trade days chosen during one of the most problematic period of the U.S. stock market operation. Obtained results allow for optimism regarding its practical use for high-frequency stock trading provided availability of a convenient computer – based support.
منابع مشابه
Studying the Monthly Effect on the Market Reactions Using Time-Space -Frequency Analysis (Case Study: Tehran Stock Exchange)
Anomaly is an incident or event that cannot be explained by the dominant theories. Anomalies are situated in confronting with the efficient market theory, so that it provides conditions for stock trading strategies with additional returns in case of existing predetermined returns. Therefore, in this study, the anomaly due to monthly effects on the stock volume trading and the Tehran Stock Excha...
متن کاملRanking and Managing Stock in the Stock Market Using Fundamental and Technical Analyses
The stock selection problem is one of the major issues in the investment industry, which is mainly solved by analyzing financial ratios. However, considering the complexity and imprecise patterns of the stock market, obvious and easy-to-understand investment rules, based on fundamental analysis, are difficult to obtain. Fundamental and technical analyses are two common methods for predicting th...
متن کاملRanking and Managing Stock in the Stock Market Using Fundamental and Technical Analyses
The stock selection problem is one of the major issues in the investment industry, which is mainly solved by analyzing financial ratios. However, considering the complexity and imprecise patterns of the stock market, obvious and easy-to-understand investment rules, based on fundamental analysis, are difficult to obtain. Fundamental and technical analyses are two common methods for predicting th...
متن کاملTime-Varying Modeling of Systematic Risk: using High-Frequency Characterization of Tehran Stock Exchange
We decompose time-varying beta for stock into beta for continuous systematic risk and beta for discontinuous systematic risk. Brownian motion is assumed as nature of price movements in our modeling. Our empirical research is based on high-frequency data for stocks from Tehran Stock Exchange. Our market portfolio experiences 136 days out of 243 trading days with jumps which is a considerable rat...
متن کاملProfitability of Momentum and Contrarian Strategies Based on Trading Volume in Tehran Stock Exchange: A Comparison of Emerging Market
In this study, the profitability of contrarian and momentum strategies were traded in mid- term based on trading volume. The stocks were categorized into three parts (high, middle and low) at the outset. Then, the relationship between excess return with three components such as cross-sectional risk, lead-lag effect and time-series pattern were examined based on Jegadeesh and Titman approach.The...
متن کامل