This article discusses the differences between AutoML and Time Series modeling.
AutoML stands for Automated Machine Learning which essentially means automating the tasks of applying machine learning to real world problems. It includes the various processes starting from uploading a dataset to building a machine learning model that is ready to be used for making predictions.
In general terms when speaking about AutoML we mean applying machine learning to real world classification and regression problems. Classification involves predicting classes/categories such as apple or orange, red or blue, churn or non churn, etc.. Regression involves predicting real numbers such as weight, price, salary, etc.. Time series analysis on the other hand involves predicting a real number that is time dependent.
How to decide if a use case is AutoML or Time series:
It is common to get confused when deciding whether a particular use case belongs to AutoML (classification/regression) or time series. Data is everywhere and almost every business has a dedicated space for storing their data. The way the data is collected and stored may not always make sense, especially to non technical people who might not be familiar with machine learning. But you can easily identify whether a use case is AutoML or time series just by looking at the data. We assume that the data is structured, that is, stored as rows and columns, for example as a spreadsheet.
Here's a chart to quickly identify whether your use case is an AutoML prediction or a Time Series prediction.