Machine Learning	Fingerprint-ing	Pre-Defined Policies	User-Defined Dictionaries and Regular Expressions
Coverage	High: Covers any document with semantic similarities to the learned data	Medium: Detects only derivatives of fingerprinted documents	Limited to the existing pre-defined types	Unlimited, providing that the user has properly defined the dictionaries and the regular expressions
Accuracy	Depends on the data	Very High	High for data types that are common enough	Medium
"Zero-Day" Protection	High	Very Low	High	High
Size/Footprint	Medium	High	Low	Low
Deployment and Config Effort	Medium (may require some tuning)	Medium	Low	High - requires careful setting and tuning