ACADEMIC DATA ANALYTICS PROJECT

Iran Housing
Market Intelligence

From raw listings to data quality, analytical populations, Gold marts, market intelligence and interactive dashboards.

Focus
Housing Market
Pipeline
M1 → M4
BI Layer
Streamlit + Power BI
01 — OVERVIEW

What this project answers

Data Reliability

How complete, consistent and trustworthy are the observed listings?

Market Geography

Which cities and neighborhoods are relatively more expensive or affordable?

Price & Supply Trends

How did asking prices and listing activity move across the available period?

Price Drivers

How do location, area, age, floor, amenities and seller type relate to price?

"

Text Signals

Are phrases such as urgent and below market actually associated with lower asking prices?

Market Segments

Can observed listings be grouped into interpretable market segments?

02 — ARCHITECTURE

End-to-end analytical workflow

01 Raw Data Observed listings
02 M1 Profiling & Audit
03 M2 Quality & Cleaning
04 M3 Analysis Populations
05 M4 / Gold Canonical Marts & QA
06 BI Layer Streamlit Dashboard
03 — KEY FINDINGS

What the analysis emphasizes

HOT

Market temperature is comparative

Hot and cold markets are presented using the project's price and listing-activity framework.

PRICE

Location is a central analytical dimension

City and neighborhood effects are separated from structural property characteristics.

TEXT

Marketing language is tested, not assumed

Text signals are evaluated statistically rather than treated as proof of value.

LIMIT

Asking prices are not transaction prices

The project keeps this distinction explicit throughout analysis and reporting.

05 — METHODOLOGY

Interpret with the right level of confidence

The project distinguishes descriptive summaries, predictive contribution and observational association, with reliability gates and limitations documented.

Read Documentation