تاثیر حرکت جانبدارانه بر پیش بینی از طریق تکنیک های کشف علمی در بازار ارز
|کد مقاله||سال انتشار||تعداد صفحات مقاله انگلیسی||ترجمه فارسی|
|15025||2003||8 صفحه PDF||سفارش دهید|
نسخه انگلیسی مقاله همین الان قابل دانلود است.
هزینه ترجمه مقاله بر اساس تعداد کلمات مقاله انگلیسی محاسبه می شود.
این مقاله تقریباً شامل 3220 کلمه می باشد.
هزینه ترجمه مقاله توسط مترجمان با تجربه، طبق جدول زیر محاسبه می شود:
- تولید محتوا با مقالات ISI برای سایت یا وبلاگ شما
- تولید محتوا با مقالات ISI برای کتاب شما
- تولید محتوا با مقالات ISI برای نشریه یا رسانه شما
پیشنهاد می کنیم کیفیت محتوای سایت خود را با استفاده از منابع علمی، افزایش دهید.
Publisher : Elsevier - Science Direct (الزویر - ساینس دایرکت)
Journal : Expert Systems with Applications, Volume 24, Issue 1, January 2003, Pages 115–122
To an increasing extent since the late 1980s, software learning methods including neural networks (NN) and case based reasoning (CBR) have been used for prediction in financial markets and other areas. In the past, the prediction of foreign exchange rates has focused on isolated techniques, as exemplified by the use of time series models including regression models or smoothing methods to identify cycles and trends. At best, however, the use of isolated methods can only represent fragmented models of the causative agents, which underlie business cycles. Experience with artificial intelligence applications since the early 1980s points toward a multistrategy approach to discovery and prediction. This paper investigates the impact of momentum bias on forecasting financial markets through knowledge discovery techniques. Different modes of bias are used as input into learning systems using implicit knowledge representation (NNs) and CBR. The concepts are examined in the context of predicting movements in the Japanese yen.
In the past, the prediction of foreign exchange rates has focused primarily on isolated techniques, as exemplified by the use of time series models including regression models or smoothing methods to identify cycles and trends. At best, however, the use of isolated methods can only represent fragmented models of the causative agents, which underlie business cycles. Experience with artificial intelligence applications since the early 1980s points toward a multistrategy approach to discovery and prediction. In particular, statistical methods such as factor analysis may be used for exploratory analysis to determine the most salient characteristics behind foreign exchange rate behavior. The results of such analysis may be used as input into a learning system using implicit knowledge representation (neural networks, NN) and case based reasoning (CBR). The rest of this paper is organized into five sections. Section 2 describes research background. In Section 2, the review of chaotic analysis and knowledge discovery techniques is presented. In Section 3, we present the case study. The case study intends to investigate the effect of bias on the predictive performance of learning methods in forecasting a foreign exchange rate. Section 4 reports the results of the case study. Finally, the concluding remarks are presented in Section 5.
نتیجه گیری انگلیسی
In the current study, the basic neural model was a feed-forward architecture using the backpropagation algorithm. The BPN procedure relies on the gradient of the error metric as a function of the weights. More specifically, the slope of the error metric is used to determine both the direction and magnitude of changes in weights at each iteration. In contrast, the Levenberg–Marquardt procedure utilizes the curvature as well as the slope (Hutchinson, 1994, Kiewiel, 1996 and Marquardt, 1963). The additional information is used to improve the search process in optimizing the weights. Consequently, the Levenberg–Marquardt approach can converge on a solution in the weight space more quickly than the basic BPN algorithm. Hence a comparison of the Levenberg–Marquardt procedure against BPN and other techniques—both in terms of speed and accuracy—represents a promising direction for future work. In fact, the literature contains numerous varieties of NNs as well as other learning techniques such as induction and genetic algorithms. The systematic evaluation of a larger collection of learning techniques represents a rich area for future investigation.