Summary

This concludes our crash course on time-series history—quite possibly the one part of this book with no formulas, graphs, or tables. Let’s briefly recap our journey; we began by exploring the early origins of time-series analysis, from ancient attempts at predicting crop yields to the first recorded instances of data logging in the Domesday Book and Chinese imperial archives. We then moved on to the classical era, examining the development of fundamental techniques that still form the backbone of many forecasting activities today.

We’ve traced the evolution from simple descriptive statistics to more sophisticated modeling techniques such as ARIMA and its variants. We discussed the emergence of state-space models and the Kalman filter, showcasing the field’s adaptability to difficult-to-model data. We moved on to talk about the development of GARCH models to address volatility clustering in financial time series. Finally, we introduced ML and DL techniques, marking the transition to the modern era of time-series analysis.

You’ve seen how time-series forecasting has been shaped by interdisciplinary contributions, from astronomy to economics. We’ve also observed how advancements in computational power have driven innovations in the field. In the following chapters of this book, we will discuss the fundamentals of time-series data and modeling, PyTorch and DL fundamentals, followed by time-series forecasting and classification models using PyTorch. You will not only read about how DL is applied to time-series data but also understand how we have taken the leap from the classical methods to DL-based methods. At this point in our journey, we are ready to discuss time-series structures and how we analyze them. In the next chapter, we will start our journey through time series proper beginning with the building blocks we need.