نظرسنجی ها: با استفاده از شبکه های عصبی برای بهبود سیستم های تجاری مبتنی بر تجزیه و تحلیل فنی با استفاده از شاخص های مالی RSI
|کد مقاله||سال انتشار||مقاله انگلیسی||ترجمه فارسی||تعداد کلمات|
|28416||2011||12 صفحه PDF||سفارش دهید||محاسبه نشده|
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 38, Issue 9, September 2011, Pages 11489–11500
Stock price predictions have been a field of study from several points of view including, among others, artificial intelligence and expert systems. For short-term predictions, the technical indicator relative strength indicator (RSI) has been published in many papers and used worldwide. CAST is presented in this paper. CAST can be seen as a set of solutions for calculating the RSI using artificial intelligence techniques. The improvement is based on the use of feedforward neural networks to calculate the RSI in a more accurate way, which we call the iRSI. This new tool will be used in two scenarios. In the first, it will predict a market – in our case, the Spanish IBEX 35 stock market. In the second, it will predict single-company values pertaining to the IBEX 35. The results are very encouraging and reveal that the CAST can predict the given market as a whole along with individual stock pertaining to the IBEX 35 index.
There has been growing interest in decision support trading systems in recent years. Forecasting price movements in stock markets has been a major challenge for common investors, businesses, brokers and speculators (Majhi, Panda, & Sahoo, 2009). The stock market is considered a highly complex and dynamic system with noisy, non-stationary and chaotic data series (Wen, Yang, Song, & Jia, 2010), and hence, difficult to forecast (Oh and Kim, 2002 and Wang, 2003). However, in spite of its volatibility, it is not entirely random (Chiu & Chen, 2009). Instead, it is non-linear and dynamic (Abhyankar et al., 1997 and Hiemstra and Jones, 1994) or highly complicated and volatile (Black & Mcmillan, 2004). Stock movement is affected by the mixture of two types of factors (Bao & Yang, 2008): determinant (e.g., gradual strength change between buying side and selling sides) and random (e.g., emergent affairs or daily operation variations). According to Wen et al. (2010), the study of the stock market is a hot topic, because if successful, the result will transfer to fruitful rewards. Thus, it is obvious that predicting the stock market’s movement is the long-cherished desire of investors, speculators, and industries (Kim, 2004). However, this market is extremely hard to model with any reasonable accuracy (Wang, 2003). Prediction of stock price variation is a very difficult task and price movement behaves more like a random walk and time varying (Chang & Liu, 2008). However, in spite of this complexity, many factors, including macroeconomic variables and stock market technical indicators, have been proven to have a certain level of forecast capability in the stock market during a certain period of time (Lo, Mamaysky, & Wang, 2000). One of the tools for this financial practice is technical analysis, also known as “charting”. According to Leigh, Modani, Purvis, and Roberts (2002), Charles Dow developed the original Dow Theory for technical analysis in 1884 revisited by Edwards and Magee (1997) more than a century earlier. Technical analysis studies historical data surrounding price and volume movements of the stock by using charts as the primary tool to forecast future price movements (Murphy, 1999). In recent years, and in spite of several critics (e.g., Malkiel, 1995), technical analysis has proven to be powerful for evaluating stock prices and is widely accepted among financial economists and brokerage firms (Chavarnakul & Enke, 2008). Due to this importance, a lot of research has gone into the development of models based on a range of intelligent soft computing techniques over the last two decades (Majhi et al., 2009). Most of the work is the combination of soft computing technology and technical analysis in stock analysis (Chen et al., 2009 and Wen et al., 2010). Following this research trend, in this paper, CAST is presented. CAST is a tool designed to improve the investment techniques used in trading systems, applied to the Spanish stock market, based on a new way to calculate the relative strength index (RSI) by Wilder (1978). This improvement is based on the use of feedforward neural networks to calculate RSI in a more accurate way, which we call iRSI. The paper consists of five sections and is structured as follows. Section 2 reviews the relevant literature about technical analysis and its intersection with soft computing. Section 3 discusses the main features of CAST, including the conceptual model, algorithm and architecture. Section 4 describes the evaluation of the tool’s performance including a description of the sample, the method, results and discussion. Finally, the paper ends with a discussion of research findings, limitations and concluding remarks.
نتیجه گیری انگلیسی
The current paper describes a research project about the generation of RSI values to create systems capable of generating automated or semi-automated investments in certain companies in the Spanish IBEX35 stock market. In this paper, the main work is based on the study case of generating a heuristic for a concrete market and applying some corrections factor in order to be able to generate good investment results for concrete companies of the sector. The generation of the RSI, known as the iRSI, also was tested using two variants in its calculation: using memory and not using it. This variant also implies the modification of the main heuristic formula created to calculate optimal RSI values. Both approaches were generated, studied and evaluated and the final conclusion reached was that RSI optimal generation (without memory) is the better option. This paper was based only on the RSI financial indicator and the heuristic methods applied where generated to create a single heuristic formula for the IBEX35 stock market. The current paper proposes four types of initiatives which should be explored in future research. In the first place, our future work plans to generate a heuristic for each company by analyzing its data. In the second place, we will extend the application of the iRSI to a broader sample: more companies pertaining to the IBEX 35, more indexes both national and international and, of course, as stated before, a bigger time frame. In the third place, we will tune the iRSI to adapt it to momentum in the market (upward or downward trend). Finally, we will expand the research to investigate broader technical analysis indexes like the MACD (Moving Average Convergence/Divergence) financial indicator or Bollinger Bands.