1.3Step 1: Collecting Production Data

The quality of your traffic model depends on the quality of your input data. The minimum viable dataset includes:

Field	Source	Purpose
session_id	Cookie or JWT	Group requests by user session
timestamp	Access log	Calculate arrival rate and session duration
path	Access log	Identify endpoint mix
method	Access log	Distinguish reads from writes
response_time_ms	APM / log	Baseline performance expectations
status_code	Access log	Filter errors from profiling
user_agent	Access log	Separate bots from humans

Collect at least 7 days of data to capture weekly patterns. For seasonal businesses, include data from peak periods.