This repository focuses on managing raw data that goes through a transformation and cleaning process, then analyzed using SQL queries to produce relevant information. The results of the analysis are then distributed into visual dashboards such as Power BI, which display insights based on business needs and common problems. The dashboards built aim to answer business questions, such as evaluating operational performance, identifying sales trends, and monitoring performance based on certain categories or segments.
This project adopts the CRISP-DM methodology as a foundational framework:
- Business Understanding
- Data Understanding / Exploratory Data Analysis
- Data Preparation
- Modeling (optional)
- Evaluation
- Deployment (Dashboard Development)
- Python (v3.10 / v3.11)
- Jupyter Notebook / Google Colab
- PostgreSQL & DBeaver
- Power BI
Beyond showcasing analytical outputs, this repository serves as a learning platform to develop and sharpen technical skills—particularly in data preprocessing and SQL querying at an intermediate to advanced level. It includes multiple study cases that implement step-by-step workflows from raw data to final insights. Each case study is accompanied by a README.md file that explains the objectives, business context, and final outcomes in detail.
Datasets and Power BI files used in this repository are stored in the following shared folder:
Google Drive – Datasets and Dashboards
Note:
.pbixfiles are native Power BI project files. They may appear as ZIP archives in Google Drive, but remain fully usable and intact when downloaded.
The datasets used in this repository are either public or synthetic (dummy) and are intended solely for educational and portfolio purposes. They do not represent any confidential or proprietary company information.