scholarly journals Selected aspects of modelling of foreign exchange rates with neural networks

Author(s):  
Václav Mastný

This paper deals with forecasting of the high-frequency foreign exchange market with neural networks. The objective is to investigate some aspects of modelling with neural networks (impact of topology, size of training set and time horizon of the forecast on the performance of the network). The data used for the purpose of this paper contain 15-minute time series of US dollar against other major currencies, Japanese Yen, British Pound and Euro. The results show, that performance of the network in terms of correct directorial change is negatively influenced by increasing number of hidden neurons and decreasing size of training set. The performance of the network is influenced by sampling frequency.

Author(s):  
Václav Mastný

This paper deals with technical analysis and its forecasting ability in the intradaily foreign exchange market. The objective of this study is to investigate whether technical indicators are able to provide prediction superior to „buy and hold“ strategy. Each indicator is tested with series of parameters in time series of different frequency (5, 15, 30, 60 min). The profitability of each indicator is examined in simple trading modell.


Author(s):  
Sonia Kumari ◽  
Suresh Kumar Oad Rajput ◽  
Rana Yassir Hussain ◽  
Jahanzeb Marwat ◽  
Haroon Hussain

This study investigates the affiliation of various proxies of economic sentiments and the US Dollar exchange rate, mainly focusing on the real effective exchange rate of USD pairing with three other major currencies (USDEUR, USDGBP, and USDCAD). The study has employed Google Trends data of economy optimistic and pessimistic sentiments index and survey-based economy sentiments data on monthly basis from January 2004 to December 2018. The study engaged Ordinary Least Squares (OLS) and Auto-Regressive Distributed Lag (ARDL) estimation techniques to evaluate the short-run and long-run effects of economy-related sentiments and macroeconomic variables on the exchange rate. The results from the study found that Economy Optimistic Sentiments Index (EOSI) and Economy Pessimistic Sentiments Index (EPSI) appreciate and depreciate the US Dollar exchange rate in the short-run, respectively. Our sentiment measures are robust to survey-based Michigan Consumer Sentiment Index (MSCI), Consumer Confidence Index (CCI), and various macroeconomic factors. The MSCI and CCI sentiments show a long-term impact on the foreign exchange market. This study implies that economic sentiments play a vital role in the foreign exchange market and it is essential to consider behavioral aspects when modeling the exchange rate movements.


2020 ◽  
Vol 3 (2) ◽  
pp. 01-09
Author(s):  
Ali Farhan Chaudhry

The current study examines short-term abnormal returns of eight major currencies including EUR/USD, GBP/USD, USD/AUD, USD/CAD, USD/CHF, USD/CNY, USD/JPY, and USD/SEK in response to the evolution of the COVID-19 pandemic using event study approach in three different scenarios. Firstly, short-term abnormal returns of major currencies are estimated on the day of World Health Organization’s (WHO) announcement declaring COVID-19 as a pandemic. Secondly, they are estimated on the day of the announcement of the first confirmed case of COVID-19 in the respective country. Thirdly, they are estimated on the day of the announcement of the first death from COVID-19 in each country. The results provided evidence that major currency investors earned positive returns in these three different scenarios. The implications of the current study are more important than anticipated. Government policymakers, foreign exchange market regulators, and foreign exchange market participants can anticipate short-term returns while establishing foreign exchange policies, designing rules and regulations, and finalizing trading and hedging strategies, respectively, in situations such as the current COVID-19 pandemic.  Received Date: September 20, 20202      Last Received:   October 23, 2020     Acceptance: November 13, 2020


2017 ◽  
Vol 17 (1) ◽  
pp. 53
Author(s):  
Yunita Astanti Unlinnuha

This paper examines the relationship between ASEAN-5 foreign exchange market and US Dollar in last 5 years. The data used is the currency of ASEAN-5 countries that are Indonesia, Malaysia, Vietnam, and Thailand. The data was analyzed using VAR (Vector Auto Regression). Among ASEAN 5, there are interdepence relationship in foreign exchange market. The strongest interdepence relationship are showed between Indonesia, Singapore and Malaysia, while Phillipines and Thailand have less influence toward others. Foreign exchange market among ASEAN 5 shows positive response which has been proven by Granger Causality test.


2009 ◽  
Vol 12 (08) ◽  
pp. 1105-1123 ◽  
Author(s):  
DANIEL J. FENN ◽  
SAM D. HOWISON ◽  
MARK MCDONALD ◽  
STACY WILLIAMS ◽  
NEIL F. JOHNSON

We investigate triangular arbitrage within the spot foreign exchange market using high-frequency executable prices. We show that triangular arbitrage opportunities do exist, but that most have short durations and small magnitudes. We find intra-day variations in the number and length of arbitrage opportunities, with larger numbers of opportunities with shorter mean durations occurring during more liquid hours. We demonstrate further that the number of arbitrage opportunities has decreased in recent years, implying a corresponding increase in pricing efficiency. Using trading simulations, we show that a trader would need to beat other market participants to an unfeasibly large proportion of arbitrage prices to profit from triangular arbitrage over a prolonged period of time. Our results suggest that the foreign exchange market is internally self-consistent and provide a limited verification of market efficiency.


Sign in / Sign up

Export Citation Format

Share Document