BANK MARKETING CAMPAIGN DATA

BANK MARKETING CAMPAIGN DATA

DataCamp project | Data Analysis Practice | 2026

Cleaned and restructured the raw export of a bank's personal loan marketing campaign (41,188 rows, 16 columns) into a well-typed relational structure ready to be loaded into a PostgreSQL database. The aim was to build a repeatable process so that this and future campaigns can be imported with minimal friction.

Key contributions:

Split a single flat CSV into three normalised tables (client, campaign and economics) that conform to a fixed target schema.

Standardised messy categorical values, removed stray punctuation from job and education labels and converted "unknown" entries into proper missing values.

Converted yes/no and success/failure columns into boolean types and rebuilt a full last-contact date from separate day and month fields.

Delivered clean, typed CSV outputs alongside a documented notebook describing every transformation.

Collaborators: Gabriela Słomiany

Software Used: Jupyter Notebook, pandas, NumPy, DataCamp

Programming Languages: Python

Repository: github.com/imgabrielas/DataAnalysisPractice

Project Date: August 2026