Module 02 · Foundations of AI Product Management

Mapping the AI Transition: From Rules to Probabilities

You are the new AI PM at 'Global-Bank'. The bank currently uses a manual 'If-Then' rule system to flag fraud, but it misses too many evolving patterns. You need to lead the transition to a probabilistic AI system, determine which AI tech stack is needed, and design a 'Human-in-the-loop' strategy to handle model errors.

45 minBeginner 3 outcomes 6 steps · 3 checkpoints

lab progress0/9 · 0%

Step-by-step

Check my work

Not sure if you're doing it right? Paste what you've written or done so far and get instant feedback scored against this lab's rubric.

Focus review on current step(switch to Guided to enable)

Dataset

bank_transactions.csv

20 bank transactions including transaction IDs, amounts, locations, and a 'current_rule' column showing existing rule-based outcomes.

Contains one missing value (row 112) and one duplicate (rows 118/119) to reflect 'Cold Start' data quality pitfalls.

trans_id(integer)	amount(number)	location(string)	current_rule(string)
101	6000	New York	Flagged
102	150	London	Approved
103	80	Unknown	Approved
104	5500	Paris	Flagged
105	10	New York	Approved
106	7200	Tokyo	Approved
107	220	Berlin	Approved
108	45	Unknown	Approved
109	5100	Madrid	Flagged
110	600	Rome	Approved
111	30	New York	Approved
112	4900	Chicago
113	12000	Dubai	Flagged
114	75	London	Approved
115	5800	Seoul	Flagged
116	320	Paris	Approved
117	90	Berlin	Approved
118	6500	New York	Flagged
119	6500	New York	Flagged
120	200	Tokyo	Approved