DSA SCI 8001 - Advanced Topics in Data Science and Analytics: Time Series Analyses and Modeling

This course introduces time series analysis and modeling for data science applications. Students will learn to analyze temporal data patterns, identify trends and seasonality, and develop forecasting models using both classical and advanced machine learning techniques. The course emphasizes practical applications of time series analysis for addressing real-world challenges in forecasting, anomaly detection, and decision-making. Through hands-on exercises, students will develop skills in data preprocessing, exploratory time series analysis, univariate and multivariate modeling, and predictive analytics. Topics include time series fundamentals, missing data handling, stationarity testing, outlier detection, classical methods (ARIMA, exponential smoothing), signal processing techniques, and modern deep learning approaches, including neural networks and reservoir computing. Students will work with multi-temporal datasets from diverse domains, including economics, energy, climate, health, and finance. The course covers both technical implementation and best practices for time series forecasting. By the end of the course, students will be able to critically analyze, model, and forecast temporal data to support data-driven decision-making in their research and professional areas.

• More Details