Syllabus

Motivation and Introduction: Time Series, Classification of Time Series, Time Series Forecasting, Forecasting Method vs Forecasting Model, Single-Step vs Multi Step-Ahead forecasting, Point vs Interval forecasting, Different forecasting methods, Components of Time Series.
Time Series Graphics: Time Plot, Seasonal Plot, Seasonal subseries plot, Scatter plots, Lag plots, Autocorrelation and Partial Autocorrelation Plots, White noise.
Simple forecasting methods: Average method, Naïve method, Seasonal Naïve method, Drift Method.
Forecasting Accuracy Measures: Point forecasting accuracy measures, Interval forecasting accuracy measures, Scale dependent and independent forecast accuracy measures.
Simple exponential Smoothing model, Trend methods, Holt-Winters Seasonal method, taxonomy of exponential smoothing models, Innovation state space model, model estimation, forecasting with ETS.
Autoregressive model, moving average model, ARMA model, non-seasonal ARIMA Model, Estimation and order selection of ARIMA model, Seasonal ARIMA models.
Time Series Analysis using Machine Learning: Overview of machine learning approaches for time series forecasting, including regression models, tree-based models, and neural networks.
Probabilistic Time Series Forecasting: Parametric models, Non-parametric models, LUBE method, Advanced LUBE method.
Advanced Time Series Models: Introduction to advanced models such as Additive, Multiplicative and Decomposition based hybrid models, and state-space models like Kalman filter.
Fuzzy Time Series Forecasting (FTSF): Fist Order Models, Higher Order Models, Definitions, FTSF considering membership values, FTSF ignoring membership values.
Hierarchical Time Series Forecasting: Bottom Up Approach, Top Down Approach, Middle Out Approach, Optimal Combination Approach, Min Trace Approach.
Multivariate Time Series Analysis: Analyzing time series with multiple variables, understanding concepts like Granger causality and cointegration.
Real-world Applications and Case Studies: Application of time series analysis in various domains such as finance, economics, environmental science, and more.

To familiarize students with the fundamental concepts of time series.

To equip students with the knowledge and skills required to apply a range of statistical time series models for accurate analysis and forecasting.

To equip students with the knowledge and skills required to apply machine learning based crisp and fuzzy time series models for accurate analysis and forecasting.

To equip students with the knowledge and skills required to apply hybrid machine learning and statistical based time series models for accurate analysis and forecasting.

1. Employ statistical models for forecasting of real world time series data.
2. Employ machine learning and hybrid models for forecasting of real world time series data.
3. Employ fuzzy time series models for forecasting of real world time series data.
4. Choose appropriate forecasting method and model based on the characteristics of data.

Robert H. Shumway and David S. Stoffer, Time Series Analysis and Its Applications: With R Examples, Springer

Walter Enders, Applied Econometric Time Series, Wiley

Rob J Hyndman and George Athanasopoulos, Forecasting: Principles and Practice, OTexts

Douglas C. Montgomery, Cheryl L. Jennings, and Murat Kulahci, Introduction to Time Series Analysis and Forecasting, Wiley

Journal of Forecasting, Wiley

International Journal of Forecasting, Elsevier