Customer Flow Prediction at Emirates ID Centers

Emirates ID centers face significant resource management challenges due to fluctuating customer traffic, leading to long wait times, customer dissatisfaction, and inefficient resource use. This thesis explores the application of time series analysis to predict customer traffic at Emirates ID centers, focusing on the Autoregressive Integrated Moving Average (ARIMA) and Long Short-Term Memory (LSTM) models. The primary research question is: “Can historical queue data from the Qmatic system be effectively used to forecast customer traffic at Emirates ID centers?” To answer this question, 800,000 observations of historical ticket issuance data from the Qmatic queue management system were analyzed. The study employs ARIMA and LSTM modeling techniques to uncover daily patterns, trends, and seasonality in customer traffic. The ARIMA model was optimized to capture long-term trends and weekly seasonality, while the LSTM model was designed to handle complex, non-linear dynamics. The findings reveal that both models can predict customer traffic, but the LSTM model significantly outperforms ARIMA in terms of accuracy. The baseline LSTM model achieved a Mean Absolute Error (MAE) of 162.96 and a Root Mean Squared Error (RMSE) of 239.21, reducing forecast errors by approximately 56% compared to ARIMA. However, ARIMA remains valuable for its simplicity and ability to capture overall trends. These results demonstrate the potential of predictive analytics to enhance resource allocation, optimize staff scheduling, and reduce customer wait times at Emirates ID centers. Future research should explore hybrid models that combine the interpretability of ARIMA with the adaptive capabilities of LSTM, incorporate external variables, and investigate real-time implementation to further improve forecasting accuracy and operational efficiency.