Panel time series data, which involves observations from multiple entities over time, is widely used in fields like economics, business analytics, politics, and healthcare for tasks such as policy analysis, disease tracking, forecasting, and anomaly detection. Initially, statistical models were employed, followed by machine learning and deep learning approaches. Despite the advancement of deep learning models, their performance is inconsistent across different dataset characteristics, such as non-stationarity and heterogeneity. This project aims to identify the strengths and weaknesses of existing models and develop a new, more robust model that consistently outperforms current approaches.
Sathurgini Uthyakumar
I am a final-year Computer Science and Engineering undergraduate at the University of Moratuwa. I am interested in full-stack software development. I have six months of experience as a Software Engineering intern and gained hands-on experience with various technologies. Additionally, I am keen on learning and applying deep learning concepts and models. Currently, I am focusing on assessing the performance and robustness of deep neural network models for panel time series data analysis.
Brief Description of Project
Recent News
- All
