Prediction of Petrol and Diesel Prices in Dar Es Salaam Using Arima Models.

Abstract

Purpose: The study aims to address the importance of predicting fuel prices due to their impact on the economy and welfare of people in Dar es Salaam city and regions in Tanzania. Design/Methodology/Approach: This study follows the quantitative research design by utilizing secondary data. The sample data consists of monthly petrol and diesel prices in Dar es Salaam from January 2015 to May 2023. The ARIMA model was employed to analyze the time series data with model identification, estimation, and verification steps performed using statistical techniques such as the ADF test, ACF, PACF, and AIC. Findings: The findings indicated that the ARIMA (0,1,1) model was the best-fitted model for forecasting both petrol and diesel prices in Dar es Salaam. The forecasted values for the next six months show that models demonstrated good performance in predicting petrol and diesel prices. Research Limitation/Implication: Some of the potential limitations of this study include the reliance on secondary data, the assumptions of stationarity and linearity in the ARIMA model, and the sensitivity of the forecast to future data. Also, the study focuses specifically on Dar es Salaam which may limit the generalizability of the findings in other regions. Social Implications: This study has significant social implications for residents of Dar es Salaam, offering insights for household budgeting, transportation planning, and predicting fuel price changes. It also informs social programs and subsidies, contributing to equitable and sustainable community development. Practical Implications: The study has practical implications for the stakeholders in the fuel industry, policymakers, and consumers in Dar es Salaam. The accurate prediction of petrol and diesel prices can assist consumers in making informed decisions regarding pricing, budgeting, and fuel consumption which helps to reduce the risk of fuel loss and optimize their fuel-related choices. Originality/Value: The novelty of this study is analyzing historical fuel price data in Dar es Salaam using ARIMA models. Through this approach, we identify trends, seasonality, and cyclical patterns unique to the region. This knowledge adds to the existing understanding of fuel price determinants in the local context.