Forecasting Malaysian exchange rate using machine learning techniques based on commodities prices

Ramakrishnan, Suresh; Butt, Shamaila; Chohan, Muhammad Ali; Ahmad, Humara

doi:10.1109/icriis.2017.8002544

Cited by 18 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is the reason that RandomForest outperformed the other two techniques. These findings are in-line with those presented in [33] who used the RandomForest for the commodity prices. Further investigation of the randomforest revealed its comparative slow performance on the testing data than the training data.…”

Section: Resultssupporting

confidence: 91%

Prediction of Malaysian Exchange Rate Using Microstructure Fundamental and Commodities Prices: A Machine Learning Method

2019

IJRTE

View full text Add to dashboard Cite

The key objective of this research is to investigate the short run dynamics of the exchange rate using commodity prices and microstructure market variables for developing economies, Malaysia. The analysis of the literature revealed different school of thought where one claims the strong correlation among the variables while other significantly reject the relationship. There is mixed results that support and reject the accurate forecasting of the exchange rate through different determinants. Therefore, in this study the machine learning approach is applied to perform the extensive experiments and investigate the relationship between the commodity prices, bid-ask spread and exchange rate. Three techniques were selected from the machine learning i.e. artificial neural network, RandomForest and support vector machine. The experimental results revealed that randomforest perform better than SVM and ANN, both in the performance and accuracy. Thus, the exchange rate can be predicted will reasonable accuracy using the commodity prices in the combination of the bid-ask spread. Thus, the policy maker can be utilized these results for strategies development, corporate planning and building investment plan.

show abstract

Section: Resultssupporting

confidence: 91%

Prediction of Malaysian Exchange Rate Using Microstructure Fundamental and Commodities Prices: A Machine Learning Method

2019

IJRTE

View full text Add to dashboard Cite

show abstract

“…Random Forest (RF) is an ensemble method formed by many decision trees that are used for both classification and regression processes, which was introduced by Breiman in 2001 [112]. RF has been applied in time-series forecasting for dynamic pricing, including forecasting the prices of power load [56] and electricity [57], diamond [58], exchange rate [59], gold [60], and stock [61] from 2006 to 2021. RF works better for data with high volatility and randomness, such as exchange rate, and it has outperformed the SVM [59].…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Exploring Time-Series Forecasting Models for Dynamic Pricing in Digital Signage Advertising

et al. 2021

View full text Add to dashboard Cite

Audience attention is vital in Digital Signage Advertising (DSA), as it has a significant impact on the pricing decision to advertise on those media. Various environmental factors affect the audience attention level toward advertising signage. Fixed-price strategies, which have been applied in DSA for pricing decisions, are generally inefficient at maximizing the potential profit of the service provider, as the environmental factors that could affect the audience attention are changing fast and are generally not considered in the current pricing solutions in a timely manner. Therefore, the time-series forecasting method is a suitable pricing solution for DSA, as it improves the pricing decision by modeling the changes in the environmental factors and audience attention level toward signage for optimal pricing. However, it is difficult to determine an optimal price forecasting model for DSA with the increasing number of available time-series forecasting models in recent years. Based on the 84 research articles reviewed, the data characteristics analysis in terms of linearity, stationarity, volatility, and dataset size is helpful in determining the optimal model for time-series price forecasting. This paper has reviewed the widely used time-series forecasting models and identified the related data characteristics of each model. A framework is proposed to demonstrate the model selection process for dynamic pricing in DSA based on its data characteristics analysis, paving the way for future research of pricing solutions for DSA.

show abstract

“…Although unknown in economics until recently (Boulesteix et al, 2012;Biau and D'elia, 2010), this flexible and powerful method is proven to outperform classification methods from 17 families, such as Bayesian models, generalized linear models, decision trees or principal component regression (Fernández-Delgado et al, 2014), but also logistic regression, Gaussian discriminant analysis, quadratic discriminant analysis and support vector machines in time-series forecasting (Khaidem et al, 2016), the ANN and ARMA approaches in forecasting real-time prices on the NY electricity market (Mei et al, 2014), neural networks and support vector machines in forecasting Malaysian exchange rate (Ramakrishnan et al, 2017), econometric methods in forecasting primary energy commodities and anticipating their turning points (Herrera et al, 2019) and neural networks, discriminant analysis and logit models in forecasting stock index movements (Kumar and Thenmozhi, 2006). Baybuza (2018) finds the random forest method to be a useful forecasting tool for Russian inflation as autoregression.…”

Section: Introductionmentioning

confidence: 99%

Random Forest as a Model for Czech Forecasting

Gawthorpe¹

2021

Prague Economic Papers

View full text Add to dashboard Cite

Random forest models have recently gained popularity for economic forecasting. Earlier studies demonstrated their potential to provide early warnings of recession and serve as a competitive method to older prediction models. This study offers the first evaluation of the random forest forecast for the Czech economy. The one-step-ahead forecasting results show high accuracy on the Czech data and are proven to outperform forecasts from the Czech Ministry of Finance and the Czech National Bank. The following multistep random forest forecast, estimated for the next four quarters, shows results similar to those from the central institutions. The main difference stems from the household and industrial confidence variables, which significantly impact on the random forest forecast. The variable-importance analysis further emphasizes the soft variables as valuable determinants for Czech forecasting. Overall, the findings motivate other forecasters to exercise this method.

show abstract

Forecasting Malaysian exchange rate using machine learning techniques based on commodities prices

Cited by 18 publications

References 17 publications

Prediction of Malaysian Exchange Rate Using Microstructure Fundamental and Commodities Prices: A Machine Learning Method

Prediction of Malaysian Exchange Rate Using Microstructure Fundamental and Commodities Prices: A Machine Learning Method

Exploring Time-Series Forecasting Models for Dynamic Pricing in Digital Signage Advertising

Random Forest as a Model for Czech Forecasting

Contact Info

Product

Resources

About