Site icon

The Berka Dataset Visualisation

An anonymised dataset from a Czech bank, known as the Berka Dataset was downloaded from here. This dataset was prepared by Petr Berka and Marta Sochorova. The data about clients and their accounts include:

Each of the above is stored in a separate CSV file, which was loaded to PowerBI. Data cleaning was performed on various relations, mainly translating Czech to English, and date conversion. The relationships between each table were then identified. More information about this dataset can be found on data.world and here.

A report with a number of pages highlighting some aspects from each relation was then created.

Exit mobile version