STEPHEN OMONDI ODHIAMBO2026-03-302026-03-302024-07https://repository.cuea.edu/handle/123456789/596ThesisMobile money services stand out as the revolutionary practices in the changing financial section in Kenya by revolutionizing conventional transaction practices as well as improving the rates of financial inclusion. This study aimed at conducting an assessment and forecasting of mobile money transactions in Kenya whereby a hybrid of ARIMA and XGBOOST was used to identify intricate patterns. The study looks at time variations in mobile money using CBK data collected over the period and identifies temporal trends in mobile money transactions. Therefore, while the use of mobile money services has rapidly expanded in Kenya over the years, there is a dearth of knowledge regarding the development trends and forecast of such transactions. It is essential for the stakeholders to have a good forecast model, so that planning and resource management are efficient. This study focused on this gap through the use of a new model that combines the linear nature of the ARIMA model with the non-linear nature of the XGBOOST algorithm. This study was guided by two specific objectives: Formulate a Hybrid ARIMA-XGBOOST models to identify patterns and movements in Mobile Money Transactions in Kenya; Also, to analyze temporal trends, present in the data and forecast future values in Kenya from the transactional data. The approach included applying the ARIMA on the time series data to get initial forecasts, then applying the XGBOOST on the residuals of the ARIMA to obtain better forecasts. The final result of hybrid model is the integration of the forecasts from the two individual models. ADF was used to test for the stationarity of the data, meanwhile the Box-Jenkins methodology was used to help identify and estimate the parameters of the best fit ARIMA model. An evaluation showed that there was a strong usurp of the both the number of transactions and the value of those being conducted through mobile money. Based on the findings from the ADF coefficient, the stationary condition was met, and therefore we proceeded to develop the ARIMA models. Initial diagnoses included model identification and examination of autocorrelation to determine the ARIMA configurations, whereas the Box-Jenkins test confirmed the models’ adequacy. The forecasting of demand for garments with the help of XGBOOST models with different types of losses proved to be reliable and accurate. When attesting to the concept of mobile money transactions growth in the context of the present study, the decomposition plots and the statistical analysis with reference to the Mann-Kendall test supported the positive trends growth. Based on Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Percentage Error (MPE) the performance of the models had high prediction accuracy. The combination model of ARIMA and XGBOOST was useful in establishing a strong methodology for the study and prediction of the mobile money transactions in Kenya. The findings also revealed a strong positive correlation between the development of mobile money services and the economic activities as well as financial sustainability. According to the forecasts of for 2024-2026, cash volume and value both will increase constantly but showing uneven tendencies depending on external conditions. Hence, these observations offered useful directions on efforts toward the alteration of mobile money in Kenya to help decision makers in the m-Chips stakeholders. This research adds knowledge to the theoretical knowledge of mobile money systems and who has significance policy, financial, and business applications for Kenya.en-USStatistical modelingforecastingmobile money transactionshybrid ARIMA-XGBoost modelThesis