SLIIT International Conference on Advancements in Sciences and Humanities [SICASH] 2024

Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/3833

Browse

Filters

20242

Advanced Search

Filter by

Settings

Has files: YesSubject: search.filters.subject.Time series analysis

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationOpen Access
    Development of an ARIMA Model to Predict the Monthly Price of Bitcoin in USD
    (Faculty of Humanities and Sciences, SLIIT, 2024-12-04) Kapukotuwa, R.W.M.C.L.B.; Muthuranwela, M.M.P.L.; Samarakoon, H.G.I.L.; Dilshan, P.G.S.; Sajeewani, A.K.R.K.; Peiris, T. S. G.
    This study examines the bitcoin price in USD in the world by developing a suitable ti me series model to identi fy its future trends. This data set consists of monthly bitcoin prices from August 2010 to July 2024. It was found that the original series is not stati onary and not seasonality. The stati onary was achieved by the fi rst diff erence. Of the parsimonious models identi fi ed based on the Parti al Autocorrelati on Functi on (PACF) and Autocorrelati on Functi on (ACF) of the stati onary series, an auto-regressive integrated moving average (ARIMA) (2,1,2) model was identi fi ed as the best-fi tt ed model. The signifi cance of the model and its parameters and informati on criteria such as the Akaike Informati on Criterion (AIC), Schwarz Criterion, and log-likelihood was used to identi fy the best-fi tt ed model. The model was trained using data from August 2010 to March 2024. The residuals of the model were found to be white noise. The mean absolute percentage error (MAPE) for validati on data is 7.09%. The percentage errors for the validati ng set are all positi ve and varied from 3.5% to 12.9%. The predicted Bitcoin price (USD) from August to October 2024 are $59947.88, $60308.7, and $60669.53. Bitcoin price can be uti lized by market demand and supply, regulatory environment, and technology development.
  • Thumbnail Image
    PublicationOpen Access
    Forecasting the Monthly Real Wage Rate of the Public Sector in Sri Lanka
    (Faculty of Humanities and Sciences, SLIIT, 2024-12-04) Gamage, S.K.A.; Gunasekara, K.L.R.K.; Gamage, P.S.H.; Ariyarathna, H.B.M.S.; De Mel, W.N.R.; Peiris, T.S.G.
    This study assesses the monthly real wage rate of the public sector of Sri Lanka by elaborati ng a suitable ti me series model to identi fy the future trends associated with the real wage rates of Sri Lanka. The sample data set consists of monthly real wage rate data from January 2018 to March 2024 from the Central Bank of Sri Lanka (CBSL). The real wage rate has been calculated selecti ng 2016 as the base year. Suitable parsimonious models were identi fi ed through the patt erns of the sample parti al autocorrelati on functi on (PACF) and sample auto-correlati on functi on (ACF) of the stati onary series. Based on the indicati ons such as Akaike informati on criterion (AIC), Schwarz Criterion (SC) and log likelihood an autoregressive integrated moving average (ARIMA) model of the type (0,1,2) was disti nguished as the best fi tt ed model. The residuals of the best fi tt ed model were ascertained to be white noise. The model has been validated for the fi rst three months of 2024. The Mean Absolute Percentage Error (MAPE) for the validati on data is 9.59%. The forecasted wage rate values from April 2024 to September 2024 are 54.562, 54.096, 53.631, 53.165, 52.7 and 52.234 respecti vely. The study’s fi ndings can be uti lized by policymakers, economists, and government workers to improve their fi nancial planning.