Information System

Permanent URI for this collection

https://etd.aau.edu.et/handle/123456789/4134

Browse

Browsing Information System by Subject "Deep Learning"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Passenger Satisfaction Prediction Model for Ethiopian Airline Utilizing Machine Learning Algorithms
    (Addis Ababa University, 2025-08-01) Dureti Guye; Melkamu Beyene
    Passenger satisfaction prediction is a critical task for Ethiopian Airlines to maintain service excellence and sustain a competitive advantage. Simple Traditional methods, such as statistical tools, often lack the analytical depth required to uncover complex patterns in large-scale passenger data. This study aims to develop a machine learning-based predictive model capable of assessing passenger satisfaction proactively, allowing Ethiopian Airlines to implement timely improvements and maintain service excellence. To conduct this study, passenger data was collected from Ethiopian Airlines' customer survey system, resulting in a dataset of 20,000 records between January 2022 and January 2023. Each response includes ratings on service quality, delays, staff interaction, and overall satisfaction, along with demographic details such as age and travel class. Data was gathered via both digital and paper surveys distributed at various touchpoints, including check-in, baggage claim, and post-flight followup. The dataset’s key attributes include passenger ratings, delay durations, demographic variables, and service-related feedback, providing comprehensive metadata for analyzing passenger satisfaction After acquiring the data, several preprocessing steps were applied to ensure data quality and compatibility with machine learning algorithms. Subsequently, we selected machine learning models that aligned with the objectives of the study and trained them to uncover the key factors influencing passenger satisfaction. The models were also used to evaluate the predictive performance of different algorithms. The dataset was split into 80% for training and 20% for testing. Finally, the trained models were evaluated to compare their accuracy and to identify the most influential features affecting passenger satisfaction. Based on the experiments conducted, ensemble models particularly XGBoost and Random Forest demonstrated the highest performance, achieving approximately 89% accuracy, meanwhile the deep learning algorithm (MLP, TabNet and DCN) achieves 85% accuracy in predicting passenger satisfaction. Ensemble models like XGBoost and Random Forest circumvented some of the common challenges faced by deep learning approaches such as data requirements, complexity, and interpretability thereby achieving higher predictive accuracy and providing more transparent insights into passenger satisfaction drivers. The dataset used in this study contained 20,000 records with 22 independent variables. Such data is sufficiently rich for ensemble models to learn complex non-linear relationships but not large enough to fully exploit the representational capacity of deep learning models (MLP, TabNet, and DCN) lacked sufficient data to optimize their numerous parameters, leading to slightly lower performance compared to ensemble methods. The most significant features found to be Type of Travel, Class, Customer Type, and Total Delay. This study confirms again that ensemble models like Random Forest and XGBoost are very effective for classification issues. Features such as Type of Travel, Class, Customer Type, and Total Delay were more influential on passenger satisfaction than traditionally assumed features such as Booking Service, Baggage Service, and Lounge Service. This result highlights the strength of machine learning and explainable AI (XAI) techniques in uncovering hidden patterns and identifying the real drivers of customer satisfaction in big and complex datasets
  • No Thumbnail Available
    Item
    Rainfall Prediction using Combined Satellite and Station Data: Adeep Learning Approach
    (Addis Ababa University, 2023-07-01) Mubarek Jemal; Melkamu Beyene (PhD)
    Currently, Ethiopia has high rainfall variance, which is a result of global climate change that has an influence on the environment, property values, and human lives. Accurate rainfall prediction is highly important to smart agriculture practices for developing countries. For rainfall prediction, using station data alone often lacks the required accuracy and spatial coverage, and satellite data has spatial coverage but cannot predict rainfall as accurately as station data. The objective of this research is to develop a model for rainfall prediction using deep learning approaches by combining weather station and satellite data. A design science research methodology was used to develop a rainfall prediction model with 30 years (1990 - 2020) of daily weather station data from the National Meteorological Agency Ethiopian and satellite data from TAMSAT v3.1 and JRA-55 climate models. In data engineering, missing values were handled using mean imputation by dividing the dataset based on the three seasons of Ethiopia. Deep learning approach that includes multi-layer perceptron (MLP), Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), and Bidirectional Long Short Term Memory (BiLSTM) were experimentally evaluated to predict rainfall for selected areas. Lastly, we proposed a model using Bidirectional Long Short Term Memory (BiLSTM) architecture that capable of forecasting daily rainfall for Ethiopia. The performance of the model is evaluated using the state of the art performance evaluation metrics such as; Root Mean Square Error (RMSE), Mean Square Error (MSE), and Mean Absolute Error (MAE), and the results were 0.0472, 0.0025, and 0.021 respectively. We also compared the proposed model with other deep learning approaches like MLP, CNN, and LSTM. The proposed BiLSTM model outperformed LSTM with an RMSE of 0.0015; CNN with RMSE of 0.0023, and MLP with RMSE of 0.0025. The experimental results show that the Bidirectional Long Short Term Memory (BiLSTM) model has a lower RMSE, MSE, and MAE.