Dr. James K. C., with more than three decades of teaching and research experience, presents a clear and practical guide to modern forecasting techniques for today's data-driven world. Forecasting plays a vital role in understanding the future and making informed decisions in business, government, and society. This book provides a comprehensive introduction to forecasting techniques, bringing together classical time-series models, machine learning, deep learning, and judgmental approaches in a unified framework, with extensive real-world examples and Python implementations.

Salient Features

- AI and Deep Learning for Forecasting: Introduces neural networks, RNNs, LSTMs/GRUs, and Transformer architectures for modeling complex temporal patterns.

- End-to-End Forecasting with Python: Provides a complete workflow from time-series data preparation and analysis through model fitting, diagnostics, forecasting, and evaluation, using pandas, NumPy, statsmodels, and scikit-learn, with specialized tools such as Prophet and Darts.

- Time-Series Modeling and Analysis: Covers trends, seasonality, decomposition, moving averages, exponential smoothing, ARMA, ARIMA, and SARIMAX models.

- Regression and Machine Learning for Forecasting: Explores regression, decision trees, and ensemble learning methods for forecasting applications.

- Strategic, Tactical, and Qualitative Forecasting: Discusses forecasting at different decision levels and structured approaches to expert judgment, including the Delphi technique, particularly for uncertain or low-data environments.

- Forecast Evaluation and Model Comparison: Explains forecasting accuracy measures, residual diagnostics, and practical approaches for comparing competing forecasting models.

- Applied Case Studies: Demonstrates realistic forecasting workflows involving demand, supply, and operational time-series data across different domains.

- Practical Learning Supplements: Includes Python programming primers, step-by-step walkthroughs, and nine sets of hands-on exercises suitable for self-study.