اطلاعیه

مقاله انگلیسی پیش بینی نوسانات نرخ تسعیر دلار آمریکا با مدل های محاسباتی و رفتار انسانی

این مقاله علمی پژوهشی (ISI)  به زبان انگلیسی از نشریه الزویر مربوط به سال ۲۰۲۲ دارای ۱۴ صفحه انگلیسی با فرمت PDF می باشد در ادامه این صفحه لینک دانلود رایگان مقاله انگلیسی و بخشی از ترجمه فارسی مقاله موجود می باشد.

کد محصول: h796

سال نشر: ۲۰۲۲

نام ناشر (پایگاه داده): الزویر

نام مجله: Expert Systems With Applications

نوع مقاله: علمی پژوهشی (Research articles)

تعداد صفحه انگلیسی: ۱۴ صفحه PDF

عنوان کامل فارسی:

مقاله انگلیسی ۲۰۲۲ : پیش بینی نوسانات نرخ تسعیر دلار آمریکا با مدل های محاسباتی و رفتار انسانی

عنوان کامل انگلیسی:

Forecasting US dollar exchange rate movement with computational models and human behavior

برای دانلود رایگان مقاله انگلیسی بر روی دکمه ذیل کلیک نمایید

دانلود رایگان مقاله بیس انگلیسی

وضعیت ترجمه: این مقاله تاکنون ترجمه نشده برای سفارش ترجمه ی مقاله بر روی دکمه ذیل کلیک نمایید (کد مقاله:H796)

ثبت سفارش ترجمه تخصصی در تمامی رشته ها

مقالات مرتبط با این موضوع: برای مشاهده سایر مقالات مرتبط با این موضوع (با ترجمه و بدون ترجمه)  بر روی دکمه ذیل کلیک نمایید

مقالات انگلیسی مرتبط با این موضوع جدید

Abstract

Our research investigates the potential benefits of adding the Behavioral Finance approach to the Machine Learning and Big Data framework applied to the challenging problem of forecasting the US Dollar exchange rate. More specifically, we show how to improve existing voting-based ensemble models trained to predict the nextday exchange rate trend with no need for retraining or other costly computational tasks. We assume that calendar effects would constrain investors’ actions; furthermore, their constrained individual actions would collectively induce deterministic patterns in the financial time-series movement. Hence, financial time-series forecasting models could be prone to monthly repeat their performance patterns, and we could use this information to obtain better predictions and consistently achieve profit. To verify the effectiveness of our methodology, we predicted the sign of the US Dollar to Brazilian Real rate variation. Our proposed models generated a profit metric value 24% higher than the original voting-based ensemble models with 16% lower volatility, gathering two positive elements: higher return with lower risk. The experiments’ outcomes supported the hypothesis that there are considerable improvements with almost no extra computational effort by taking into account behavioral patterns in foreign exchange predictions.

Keywords: Exchange rate, Behavioral finance, Ensemble models ,Machine learning

۱.Introduction

For the last decades, the production of economic and financial time series forecasting studies based on statistical fundamentals and computational intelligence methodologies has benefited from computational power-boosting, a generically called Machine Learning (ML) trend. Documents, such as the World Economic Forum Annual Report 2019–۲۰۲۰۲ and the AI Index 20213, provide evidence confirming this trend and its acceleration due to the expansion of data availability, the Big Data phenomenon. However, despite the growth in quantity, comparatively, the outcome produced by the research in the economic and financial areas has not reached the same levels of consistency and quality observed in other application fields, such as in image and speech recognition (Han, 2018).

In this scenario, several studies based on the Neoclassical Finance Theory highlight the complex nature of the economic and financial time series forecasting problems as one of the possible reasons for this performance gap (L´opez de Prado, 2018), since, even for humans, spotting a cat in a photo is much easier than predicting the next-day exchange rate…

۷.conclusions

This research investigates the potential benefits of adding the Behavioral Finance Theory perspective to the Machine Learning and the Big Data framework applied to the challenging problem of predicting the next-day exchange rate trend; more specifically, we show how to improve existing voting-based ensemble models trained to provide this prediction.

We assume that calendar effects would imply investors’ actions; furthermore, their constrained individual actions would collectively induce deterministic patterns in the financial time-series movement. Hence, financial time-series forecasting models would present monthly performance patterns, which could be used in our favor to identify the ‘best model’ among all available models based on their past performance…

مقالات مرتبط با این موضوع

ترجمه مقاله در مورد حسابداری

مقاله انگلیسی در مورد  اقتصاد با ترجمه

مقاله انگلیسی در مورد نرخ ارز

مقاله انگلییسی در مورد مالی رفتاری

مقاله انگلیسی در مورد یادگیری ماشین

مقاله انگلیسی در مورد پیش بینی مالی

دانلود رایگان مقاله انگلیسی با ترجمه