Join Us

Bulletin of Pure and Applied Sciences- Math& Stat. (Started in 1982)
eISSN: 2320-3226
pISSN: 0970-6577
Impact Factor: 4.895 (2017)
DOI: 10.5958/2320-3226
Editor-in-Chief:  Prof. Dr. Lalit Mohan Upadhyaya
About Journal More Archive Visit IndianJournals.com
Current Issue
Guide for Authors
Journal's Ethics & Policies
Editorial Board
Reviewer Board
UGC Protocol Part 1
Article Details

Bulletin of Pure and Applied Sciences- Math& Stat. (Started in 1982)
Year : 2020, Volume & Issue : BPAS-Maths & Stat 39E(1), JAN-JUN 2020
Page No. : 1-30, Article Type : Original Aticle
Article DOI : 10.5958/2320-3226.2020.00001.6 (Communicated, edited and typeset in Latex by Lalit Mohan Upadhyaya (Editor-in-Chief).Received May 26, 2019 / Revised January 29, 2020 / Accepted February 17, 2020. Online First Published on June 30, 2020)

Comparative study of exponential smoothing models and Box- Jenkins ARIMA model of partitioned data of daily stock prices of the CRDB Bank in Tanzania

K.K. Saxena1 and Juma Salehe Kamnge2
Author’s Affiliation : 1,2. Department of Statistics, University of Dodoma, Dodoma, Tanznia.

Corresponding Author : K.K. Saxena,
E-Mail:-[email protected]


Data mining techniques and other analytical techniqueshave played a significant role in analysing data from different sources. Data from stock market consist of high volatility and hence it needs a special care to fit amodel for forecasting future stock prices values. In the stock market, investors trade to get positive returns through buying at a lower price and selling at a higher price. However, not all investors get positive returns on their investment in stock market because oflarge amount of risk involvedin the stock market due to vast fluctuation in the stockmarket prices.This study isconducted to compare and select the best model amongautoregressive integrated moving average (ARIMA), single exponential smoothed model (SES), double exponential smoothed model (DES), and Damped trend linear exponential smoothed model. The modelling process was preceded by analysing the time series which revealed the presence of non-stationarity. The resultant models were found as ARIMA(1,1,2), Simple Exponential Smoothing(SES) and Double exponential smoothing (DES) whoseparameters' estimateswere also found to bestatistically significant. Akaike's Information Criterion (AIC) and Bayesian Information Criterion (BIC) were used toselect the best model among all the three fitted models. The performance of the fittedmodel isanalyzed and the market behavior for future forecast is studied. ARIMA(1,1,2) is selected as the best model for daily stock forecasting forthe CRDB bank in Tanzania.


Time series analysis, ARIMA model, Simple, Double and Damped trend linear exponential smoothing methods, ACF and PACF. 2020 Mathematics Subject Classification: 62M10, 62M99, 62P99, 91B84.
Download Now

All rights reserved. Website Designed and Maintained by LASERWEBMAKER.COM

Publisher Ethics & Policies    |Downloads    |    Article Submission   |    Payment    |    Contact Us