- Naif Albader
- Yazeed Musallam
iAQAR for real-estate anaylsis.
Many of real-estate buyers unsure about the value of the land after years, hence; our company iAQAR propose a solution to make predection using regression techinques.
The primarily goal of project to answer the following questions/needs:
- What is the Housing price in riyadh in the next 10 years?
- Is the price increasing each year?
- What is the price growth for each year?
- Datasets with description:
This project based on the data availabile on the ministy of justice website:
The land prices are scrapped from: https://www.moj.gov.sa/ar/opendata/bi/birealestate/Dashboards/100_kpiDistrict/101_Monthly/kpi101_04.aspx.
Sample size:
11 years scrapped (2010 to 2021) worth of data will be used for the analysis, and the reason is to make a robust model for the future predections.
Only riyadh city will be involved in this project.
Description for the datset as num of rows, number of features/columns, names of columns with description:
Description of scrapped data:
The dataset represent the sales deals of lands in riyadh in last 11 years
Number of features: 8 features/Columns
Number of rows: Approx.: 600K rows
Names of columns with description and type:
Field Name | Description |
---|---|
Neighborhood | Neighborhoods of Riyadh |
Scheme | Specific Scheme inside a Neighborhood |
Land | Specific Land inside a Scheme |
Date | Date of a land sale |
Id | Unique id for a specific sale |
Price (SAR) | The total price of a land in SAR |
Area (m2) | The area of a land in m^2 |
Price (m2) | The price of a land for each m^2 |
The main technologies and libraries that will be used are: Technologies:
- Python
- Jupyter Notebook
- HTML/CSS
- Flask
Libraries:
- Pandas
- pickle
- BeautifulSoup and selenium
- OS
- Matplotlib
- Seaborn
- NumPy
- Sklearn
- Category Encoders
- Tensorflow/keras
- Plotly
Processing tools:
Google Colab
Note:
During the project analysis, some additional tools may be used.