Boost Time-Series Modeling with Effective Temporal Feature Engineering – Part 3
Introduction Time-series modeling is a statistical technique used to analyze and predict the patterns and behavior of data that change over time. Part 1 of this blog series explained standard time-series models such as AR models, ARIMA, LTSM, and Prophet and discussed their advantages and disadvantages. Part 2, on the other hand, introduced an alternative approach - feature engineering from temporal datasets, that provides numerous benefits over standard time-series modeling. In Part 3, the last of this blog series, we will examine ARIMA and Prophet models, compare them with an alternative feature engineering approach, and demonstrate the advantages of the feature engineering approaches. Dataset In this blog, we utilized the dataset taken from the Prophet quick start demo guide. The data is a time series based on the log of daily page views for the Wikipedia page for Peyton Manning. The data is a periodic time series spanning eight…
