Data Analyst & AI Specialist | Python, SQL & Business Intelligence
I am an Artificial Intelligence undergraduate with hands-on, remote industry experience building end-to-end data pipelines and driving data-backed decisions. I specialize in bridging the gap between chaotic, messy data and clean, structured analytics that businesses can actually use to scale. Having worked with cross-functional and remote teams, I understand how to manage datasets at scale whether that means designing automated ETL workflows, optimizing relational databases, or building interactive dashboards for executive stakeholders.
Skills
Experience Level
Language
Work Experience
Education
Qualifications
Industry Experience
- Identify Inflation Catalysts: Isolate specific utility, food, and non-food items driving core inflationary pressures.
- Geographical Mapping: Conduct cross-city comparative analysis to evaluate cost-of-living variances.
- Quantify Volatility Dynamics: Distinguish between stable commodities and hyper-volatile goods.
- Extraction: Gathered weekly SPI PDF reports from the Pakistan Bureau of Statistics (PBS) and converted unstructured text tables into CSV format.
- Integration: Concatenated dozens of individual data files into a single, unified dataset using Python.
- Data Quality: Resolved date formatting inconsistencies, eliminated duplicate records, standardized item names, and verified unit metrics.
- Utilities and Consumer Essentials
- Non-food consumer essentials experienced dramatic shifts, with specific footwear categories (Bata Ladies Sandals) surging by +52.5% YoY.
- Fixed baseline costs such as Gas Charges underwent a massive upward correction, spiking by +38.3% YoY.
- Dietary and Protein Pressures
- Basic nutritional building blocks scaled rapidly. Refined Sugar registered a notable +17.4% YoY rise, closely followed by Beef with Bone growing at +14.7% YoY.
- Geographical Disparities and Data Anomalies
- Islamabad stands as the country’s most expensive major city, yielding a high average price index of ₨646.7.
- Quetta returned a suspicious historical average index of ₨33.9, flagging a critical regional reporting anomaly by data collection sources that requires isolated validation.
- Hyper-Volatile Clusters
- Energy and essential cooking products (Gas, LPG, Wheat Flour, and Cooking Oils) exhibited severe price instability, maintaining massive price spreads exceeding ₨600 within short reporting cycles.
- Languages and Libraries: Python, Pandas, NumPy, Matplotlib, Seaborn
- Environment and Tools: Jupyter Notebook, Git, GitHub
Project Overview
This project analyzes weekly price changes across 16 regional hubs and 56 essential commodities from January 2023 to August 2025. The objective is to identify core inflation drivers, evaluate regional affordability variances, map price volatility, and structure historical time-series data for automated forecasting.
Dataset Scale: Approximately 85,154 rows containing Date, City, Item, Avg_Price, Min_Price, Max_Price, and Unit.
Project Goals
Data Engineering and Cleaning
Raw macroeconomic data was extracted from fragmented government reports. The ETL pipeline was engineered as follows:
Core Insights
Tech Stack
<img width=“1389” height=“590” alt=“output” src="https://www.twine.net/signin />
Hire a Data Analyst
We have the best data analyst experts on Twine. Hire a data analyst in Islamabad today.