This project was my full journey of analyzing a property dataset — from raw messy data all the way to an interactive Power BI dashboard.
It includes data cleaning, exploration, RFM analysis, time-series analysis, and business insights about property performance.
The first step was all about understanding and preparing the data.
I used Python (Jupyter Notebook) to:
- Handle missing and duplicated values
- Convert date columns and normalize data types
- Explore key trends and distributions
📂 Notebook: 02_EDA_Cleaning.ipynb
📂 Dataset Folder: 01_Dataset
The cleaned files were exported as CSVs and later used for the analysis stages.
📂 Cleaned Data Folder: 03_Cleaned_Dataset
Next, I performed an RFM (Recency, Frequency, Monetary) analysis for both:
- Clients – to segment customers based on activity and value
- Property Owners – to understand owner engagement and performance
This helped identify loyal clients, potential churners, and high-value owners.
I also visualized the RFM results to find patterns across user segments.
📂 Notebook: 04_RFM_Analysis.ipynb
In this step, I analyzed sales performance over time.
I broke down:
- Monthly sales trends
- Seasonal patterns
- Regional differences
- Moving averages for better trend detection
📂 Notebook: 05_Sales_TimeSeries_Breakdown.ipynb
After the data and insights were ready, I built a Power BI dashboard that brings everything together visually.
The dashboard is structured into 6 pages, each focusing on a specific insight area:
-
Home quick entry with slicers & theme switch
-
Overview high-level summary of sales & rentals
-
Performance KPIs, growth trends, and metrics
-
Visits visitor activity & conversion
-
Agents agent performance analysis
-
Maintenance Cost cost tracking and efficiency
Working on this project helped me strengthen my end-to-end data analysis skills — from cleaning and understanding raw data, to uncovering insights and visualizing them effectively.
