مقاله من در زمینه پیش بینی شبکه های عصبی در پیش بینی نسبت شارپ است ، بنده ترجمه دقیقی از متن با توجه به تخصصی بودن متن لازم دارم. در عین حال زمانم محدود است ظرف حداکثر سه روز تحویلم داده شود. بنابراین باتوجه به به اهمیت دقت در ترجمه بعد از تایید متن ترجمه از لحاظ صحت و درستی در اصطلاحات پرداخت انجام میشود. بخشی از پروژه برای تایید مترجم به شرح زیر است:
This study analyzes a neural networks model that forecast Sharpe ratio. The developed neural networks model is successful to predict the position of the investor who will be rewarded with extra risk premium on debt securities for the same level of portfolio risk or a greater risk premium than proportionate growth risk. The main purpose of the study is to predict highest Sharpe ratio in the future. Study grouped the data on yields of debt instruments in periods before, during and after world crisis. Results shows that neural networks is successful in forecasting nonlinear time lag series with accuracy of 82% on test cases for the prediction of Sharpe-ratio dynamics in future and investor`s portfolio position
In this paper, we will show that neural networks can be used as a great prediction technique of portfolio performance, consisting only of fixed income assets. Furthermore, this will overcome limitation of term structure models of mostly theoretical contribution. ANN models are excellent for practical application. Our theoretical contribution lies in the construction of the modified capital allocation line model and investor's portfolio position model, whose performance we can forecast by neural network technique. In this way we will support further scientific discussion on fixed income assets portfolio performance (as theoretical contribution) and also practical implications on financial markets. Furthermore, financial market is essentially dynamic, non-linear, complicated, nonparametric and chaotic in nature (Tan, Quek, & Ng, 2005). For effective using of neural network for the financial market data analysis the tremendous noise and complex dimensionality should be decreased. From the theoretical side, Hicks (1962) and Pratt (1964) claims that the mean-standard deviations approach are inadequate and objective for using von Neumann–Morgenstern utility function with the quadratic form for (on which the most of the previous researches were based). Other authors, like Samuelson (1967), Borch (1969), Feldstein (1969) proved with stronger facts that von Neumann–Morgenstern utility function does not explain adequately the preferences in the mathematical model of mean-standard deviation approach, which influenced to appear several models with the mean absolute deviation, the interquartile range and the classical statistical measures of entropy.
masoudd59, آذر 1398