Time Series Analysis Of Turnovers In Quick Service Restaurant Industry: A Case Of Simbisa Brands Zimbabwe

Author

Holandi Brandon R

Title

Time Series Analysis Of Turnovers In Quick Service Restaurant Industry: A Case Of Simbisa Brands Zimbabwe

Abstract

This research delves into the turnover dynamics of Simbisa Brands within the Quick Service Restaurant (QSR) industry in Zimbabwe, spanning from January 2016 to December 2022. Adopting a quantitative and analytical approach, the study aims to uncover patterns, trends, and seasonality in historical turnover data, essential for strategic decision-making within the QSR sector. The research design, informed by methodologies outlined by Anderson et al., (2016), emphasizes the significance of quantitative analyses in guiding strategic processes. Primary data sourced directly from Simbisa Brands' financial records ensures the reliability and accuracy of the dataset, comprising 84 monthly observations. Utilizing statistical analysis software like Python and Microsoft Excel, researchers conduct sophisticated time series analysis and diagnostic tests, ensuring a robust analytical framework. Turnover, as the primary variable, serves as a crucial metric for assessing business growth, profitability, and market competitiveness. Diagnostic tests including the Augmented Dickey-Fuller test and autocorrelation tests validate data integrity and guide modeling decisions. The Autoregressive Integrated Moving Average (ARIMA) model is employed to capture turnover dynamics, while machine learning models like XGBoost and Random Forests are introduced and evaluated for forecasting accuracy. Ethical considerations such as data privacy and obtaining informed consent are carefully addressed. Through systematic examination, this research provides actionable insights empowering businesses to optimize resource allocation, refine marketing strategies, and enhance operational efficiency within the QSR industry. It contributes to the field of business analytics while upholding integrity, trustworthiness, and respect for all stakeholders.

Date

2024

Publisher

BUSE

Keywords

Quick service

Restaurant

Time Series

Analysis

Supervisor

June 2024