SLIIT International Conference on Advancements in Science and Humanities [SICASH]
Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/311
SLIIT International Conference on Advancements in Science and Humanities is organized by the Faculty of Humanities and Sciences of the Sri Lanka Institute of Information Technology (SLIIT), the annual research multi-conference of the faculty.
Browse
3 results
Search Results
Publication Open 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.Publication Open Access Development of Time Series Model to Predict Daily Gold Price(Faculty of Humanities and Sciences, SLIIT, 2024-12-04) Gayashan, W. A. K.; Dayarathna, A. K. G.; Rajakaruna, R. W. M. A. P.; Perera, T. J. N.; Peiris, T. S. G.Gold is ancient and one of the most precious and popular commoditi es in the world. Gold price forecasti ng is criti cal in fi nancial decision-making, providing valuable informati on for investors in the gold market, sellers of gold items and stakeholders. Not much studies have been carried out in to forecast daily gold prices of Sri Lanka. The aim of this paper is to forecast the daily gold price rate (Rupees/troy ounce) using data from 2nd January 2018 to 14th June 2024 published by the Central Bank of Sri Lanka. The best fi tt ed model was identi fi ed as ARIMA (1,1,1) + ARCH (2). The model was trained using data from 2nd January 2018 to 31st May 2024 and validated using data from the 3rd of June 2024 to 14th of June 2024. The model was stati sti cally tested using standard stati sti cal procedure and errors were found as white noise. The Mean Absolute Percentage Error (MAPE) for the training data set and validati on data set were 0.748% and 1.002% respecti vely. The validati on confi rmed that the ARIMA (1,1,1) + ARCH (2) model eff ecti vely captures the dynamics of gold price movements, off ering robust predicti ve power. These results indicate that the model is highly accurate and reliable for forecasti ng, making it a valuable tool for fi nancial insti tuti ons and investors aiming to predict market trends and make informed investment decisions.Publication Open Access Forecasting Consumer Price Index in the United States(Faculty of Humanities and Sciences, SLIIT, 2023-11-01) Witharana, W. W. S. K; Udugama, U. K. D. T. N.; Fernando, P. M. R.,; Kaumadi, H. M. H.; Peiris, T. S. G.This report presents the Auto-Regressive Integrated Moving Average (ARIMA) model for forecasting the consumer price index (CPI) in US using monthly data from March 2010 to March 2023. The original series was not stationary, but the first difference series was found to be stationary using the Augmented Dicky Fuller test. The best-fitted model was identified based on the significance of the parameters, volatility (sigma2), log-likelihood, Akaike, Schwartz, and Hannan- Quinn information criterion. Parameters of the fitted model are significantly deviated from zero. The stability of the model has been checked using the roots of the unit root test. Residuals of the fitted model satisfied the randomness but nonconstant variance. The monthly forecasted values of CPI from April 2023 to August 2023 are 301.833, 302.444, 303.038, 303.639, and 304.261. The percentage errors of the forecasted values are less than one percent. This method and results provide useful information to policy and market makers for their planning,