Time Series input models are a type of machine learning model that operates on time series data, or data which measures a certain value over time, such as credit card balance over time. These models can perform tasks such as predictions or recommendations based on past patterns.

Formatted Data in Arthur

Time Series input models require the following data formatting:

[
	{
		"timestamp": "2023-10-05T00:00:00Z", 
		"value": 1
	}, 
	{
		"timestamp": "2023-10-06T00:00:00Z", 
		"value": 4
	}
]

Arthur requires that all times will be present in a given series according to a regular interval (eg. one value each day). There is an upper bound of 500 timestamps in a single time series inference.

Arthur supports sending time series data in JSON files or DataFrames.