Time-series analysis of foreign exchange rates using time-dependent pattern entropy

In most studies on dynamics of time series financial data, the absence of chaotic behavior is generally observed. However, this theory is not yet established in the dynamics of foreign exchange rates. Conflicting claims of presence and absence of chaos in foreign exchange rates open door for further investigation considering various deterministic factors. This work examines the dynamics of exchange rate of the Philippine Peso against selected foreign currencies. Time series data were collected for eight (8) of Philippine’s top trading partners as categorized according to economic condition. The data obtained with permission from the Central Bank of the Philippines covered the years 2013 to 2017. Data sets were plotted revealing non-linear movement of Philippine exchange rates against time. The foreign exchange rate time series obtained per currency were examined for chaotic behavior by computing the Largest Lyapunov Exponents (LLE). A positive Lyapunov exponent is an indication of sensitivity dependence, i.e, a chaotic dynamics; whereas, a negative Lyapunov exponent indicates otherwise. Computed LLE’s varied per currency but all were found to be negative. Therefore, using the Largest Lyapunov Exponent Test (LLE), analysis of the time series of Philippine foreign exchange rates shows little evidence of chaotic patterns.

Download Full-text

Nonlinear Time Series Analysis with Applications to Foreign Exchange Rate Volatility

10.1007/978-3-662-12605-9 ◽

1998 ◽

Cited By ~ 17

Author(s):

Christian M. Hafner

Keyword(s):

Time Series ◽

Exchange Rate ◽

Time Series Analysis ◽

Foreign Exchange ◽

Exchange Rate Volatility ◽

Nonlinear Time Series ◽

Foreign Exchange Rate ◽

Nonlinear Time Series Analysis ◽

Series Analysis

Download Full-text

Time-series analysis of sleep–wake stage of rat EEG using time-dependent pattern entropy

Physica A Statistical Mechanics and its Applications ◽

10.1016/j.physa.2008.01.102 ◽

2008 ◽

Vol 387 (13) ◽

pp. 3145-3154 ◽

Cited By ~ 14

Author(s):

Ryuji Ishizaki ◽

Toshikazu Shinba ◽

Go Mugishima ◽

Hikaru Haraguchi ◽

Masayoshi Inoue

Keyword(s):

Time Series ◽

Time Series Analysis ◽

Time Dependent ◽

Series Analysis

Download Full-text

Currency movement forecasting using time series analysis and long short-term memory

International Journal of Industrial Optimization ◽

10.12928/ijio.v1i2.2490 ◽

2020 ◽

Vol 1 (2) ◽

pp. 71

Author(s):

Kristina Sanjaya Putri ◽

Siana Halim

Keyword(s):

Time Series ◽

Time Series Analysis ◽

Foreign Exchange ◽

Foreign Exchange Market ◽

Short Term Memory ◽

Window Size ◽

Short Term ◽

Term Memory ◽

Series Analysis ◽

Long Short Term Memory

Foreign exchange is one type of investment, which its goal is to minimize losses that could occur. Forecasting is a technique to minimize losses when investing. The purpose of this study is to make foreign exchange predictions using a time series analysis called Auto-Regressive Integrated Moving Average (ARIMA) and Long Short-term memory methods. This study uses the daily EUR / USD exchange rates from 2014 to March 2020. The data are used as the model to predict the value of the foreign exchange market in April 2020. The model obtained will be used for predictions in April 2020, where the RMSE values obtained from time series analysis (ARIMA) with a window size of 100 days and LSTM sequentially as follows 0.00527 and 0.00509. LSTM produces lower RMSE values than ARIMA. LSTM has better prediction results; this is because the LSTM has the ability to learn so that it can utilize a large amount of data while ARIMA cannot use it. ARIMA does not have the ability to learn even though given a large amount of data it gives poor forecasting results. The ARIMA prediction is the same as the values of the previous day.

Download Full-text