1. Abstract

Real estate analysis plays an important role in understanding property market trends and helping buyers, investors, and developers make informed decisions. With the increasing availability of large real estate datasets, data analytics tools can be used to identify patterns, relationships, and key factors that influence housing prices.

This project focuses on analysing a real estate dataset obtained from the UCI Machine Learning Repository and also available on Kaggle. The dataset contains information about apartment properties such as sale price, year built, year sold, apartment size, number of floors, parking facilities, management type, nearby transportation facilities, and other important attributes.

Using Power BI, the dataset is first examined and verified for data consistency, missing values, and correct data types using the Power Query Editor. Since the dataset is already highly structured and clean, minimal data transformation is required. The cleaned dataset is then used to create various interactive visualizations.

Through Power BI dashboards, relationships between variables such as sale price, apartment size, transportation accessibility, nearby facilities, and construction year are analysed. This project demonstrates how business intelligence tools like Power BI can be effectively used for real estate data analysis and visualization to extract meaningful insights.

 2. Objectives

The main objectives of this project are:

1. To understand real estate datasets and property-related variables.
2. To analyse apartment price data using Power BI.
3. To examine relationships between housing price and property characteristics.
4. To check and validate dataset structure using Power Query Editor.
5. To identify categorical and numerical data variables in the dataset.
6. To create meaningful visualizations using Power BI dashboards.
7. To analyse the influence of factors such as transportation access, apartment size, and nearby facilities on property prices.
8. To develop an interactive dashboard for real estate market analysis.

 3. Existing System

Traditional real estate data analysis methods rely on:

1. Manual property evaluation and comparison
2. Spreadsheet-based analysis using tools like Excel
3. Static reports for market analysis
4. Basic statistical comparisons of property prices

Limitations of Existing Systems

1. Difficulty in analysing large real estate datasets efficiently.
2. Limited visualization capabilities.
3. Time-consuming manual data analysis.
4. Static reports that lack interactive exploration.
5. Difficulty in identifying relationships between multiple property factors.

These limitations highlight the need for modern business intelligence tools such as Power BI for real estate data analysis.

 4. Proposed System

The proposed system uses Power BI to analyse and visualize the real estate dataset.

In this system:

1. The dataset is imported into Power BI Desktop.
2. The data is reviewed in Power Query Editor to verify data quality.
3. Missing values and incorrect data types are checked.
4. Numerical and categorical variables are identified.
5. The dataset is used to create multiple interactive visualizations.
6. Filters and slicers are implemented to analyse property data by year and other variables.

The system enables users to analyse housing prices and understand the influence of various factors such as apartment size, transportation accessibility, and nearby facilities.

 5. Implementation Procedure

The implementation of this project involves the following steps:

Step 1: Data Collection

The real estate dataset is obtained from the UCI Machine Learning Repository or Kaggle. The dataset contains detailed information about apartment properties and their sale prices.

 Step 2: Data Loading

The dataset is imported into Power BI Desktop.

The Transform Data option is selected to open the Power Query Editor for reviewing the dataset.

 Step 3: Data Understanding

The dataset includes several important attributes such as:

1. Sale price of apartments
2. Year the apartment was built
3. Year and month of sale
4. Apartment size (square feet)
5. Number of floors
6. Hall type
7. Heating type
8. Parking facilities
9. Nearby public facilities such as schools, parks, hospitals, and transportation

The dataset is examined to understand the meaning and structure of each variable.

Step 4: Data Validation

The dataset is checked for:

1. Missing values
2. Incorrect or negative values
3. Data type consistency

Since the dataset is already well-structured, minimal cleaning is required.

 Step 5: Data Transformation

In this step:

1. Column names can be renamed for better readability
2. Unnecessary columns can be removed
3. Data types are verified and corrected if required

 Step 6: Data Visualization

Several visualizations are created in Power BI, including:

1. Bar charts comparing apartment size and sale price
2. Line charts analysing housing prices over years
3. Pie charts and donut charts for categorical variables such as heating type and hall type
4. Scatter plots analysing relationships between apartment size and price

 Step 7: Dashboard Creation

An interactive Power BI dashboard is created using:

1. Filters and slicers for year-based analysis
2. Visual comparisons between different housing factors
3. Analysis of transportation accessibility and housing prices

This dashboard provides meaningful insights into real estate market patterns.

6. Software Requirements

The software tools used in this project include:

1. Power BI Desktop – Data visualization and dashboard creation
2. Power Query Editor – Data cleaning and transformation
3. Microsoft Excel / CSV files – Dataset format
4. Windows Operating System

 7. Hardware Requirements

Minimum Hardware Requirements:

1. Processor: Intel i3 or higher
2. RAM: 4 GB or higher (8 GB recommended)
3. Storage: 256 GB or higher
4. Laptop or Desktop Computer
5. Advantages of the Project
6. Provides clear insights into real estate price trends.
7. Enables interactive data exploration using Power BI dashboards.
8. Helps identify key factors influencing housing prices.
9. Simplifies large real estate datasets through visualization.
10. Supports data-driven decision making for property buyers and investors.
11. Allows easy comparison of property features and prices.
12. Demonstrates the practical application of Power BI in real estate analytics.