Chathuram

Housing Market Analysis in London boroughs

Self Level • Meio período

Mar 2026 - Mar 2026 • 0 mos

London Housing Market Analysis Price vs Demand Dynamics Across Boroughs ________________________________________ This project analyzes housing market dynamics across London boroughs, focusing on the relationship between: • 📈 House price growth • 🏘️ Housing transaction volume (demand) The goal is to identify market patterns, imbalances, and potential investment signals using a structured analytical framework. Data Preparation Key Steps: 1. Entity Filtering • Removed non-borough entries: o England o London o Regional aggregates (e.g., South East, North East) 2. Data Integration • Joined datasets using a common key: Code (borough identifier) 3. Missing Data Handling • Removed invalid join records • Retained boroughs with partial time-series gaps 4. Data Type Standardization • Converted text-based values to numeric • Eliminated #N/A errors to enable aggregation ________________________________________ ⚙️ Feature Engineering To capture market dynamics, the following features were created: 1. Price Growth (Current Price - Previous Price) / Previous Price • Calculated per borough over time • Ensures intra-borough consistency ________________________________________ Aggregation Method A pivot-based approach was used to summarize borough-level performance: Rows → Borough Values → - Avg Price Growth - Avg Houses Sold Growth - Count of observations This enables comparability across boroughs by normalizing time-series data. ________________________________________ Key Insights • Boroughs such as Westminster, Lambeth, Hackney, and City of London exhibit high price growth despite declining transaction volumes, indicating potential supply constraints or affordability pressures. • A significant number of boroughs fall into the “Undervalued” quadrant, where demand remains relatively strong but price growth is subdued, suggesting potential for future appreciation. • The City of London stands out with strong price performance despite weaker demand.

Data Cleaning, Exploratory Data Analysis & Dashboard Development

Freelance Data Analyst (Independent Projects) • Freelance

Mar 2026 - Mar 2026 • 0 mos

Project: Olist E-commerce Data Analysis & Power BI Dashboard Overview This project analyzes the Brazilian Olist E-commerce Public Dataset to understand sales performance, customer purchasing behaviour, and delivery efficiency across Brazil. Data Preparation The dataset contains multiple relational tables including orders, customers, products, sellers, payments, and reviews. These datasets were cleaned and merged using Python to create a structured analytical dataset suitable for business intelligence reporting. Key Tasks Completed • Data cleaning and missing value handling • Merging relational datasets using order_id and customer_id • Feature engineering (delivery time, total order value) • Exploratory Data Analysis (EDA) • Building an interactive Power BI dashboard Key Insights • Order activity shows seasonal variations across months • Customer satisfaction is generally high but decreases when delivery time increases • Most orders contain one or two items, indicating focused purchasing behaviour • Credit-based payment methods are widely used Tools & Technologies Python (Pandas), Data Cleaning, Exploratory Data Analysis, Power BI Dashboard Development This project demonstrates my ability to transform raw datasets into structured insights and interactive dashboards that support data-driven decision making.

Retail Sales Performance Analysis & Profitability Insights Report

Self Level • Meio período

Feb 2026 - Feb 2026 • 0 mos

Retail Sales Performance Analysis & Profitability Insights Report Business-Oriented Exploratory Data Analysis Tools: Python | Pandas | Visualization Executive Summary This project presents a structured end-to-end analysis of a retail sales dataset to evaluate revenue trends, profitability drivers, and operational risks. Key Findings: • Revenue shows steady year-over-year growth • Technology is the most profitable category • High discount levels significantly reduce profit margins • A small group of sub-categories drives a large portion of revenue • A measurable number of transactions generate negative profit Strategic Recommendations: • Optimize discount policies to protect margins • Prioritize high-profit categories and sub-categories • Reduce loss-making transactions • Implement region-specific growth strategies This notebook demonstrates a complete workflow from raw data cleaning to business insight generation. 1. Business Objective The purpose of this analysis is to: • Assess overall sales performance • Identify profitability drivers • Evaluate the impact of discounting • Analyze category and regional contribution • Generate actionable strategic insights Insight Profit is negatively influenced by discount levels, while sales and quantity show positive association. 5. Strategic Insights a. Revenue growth remains strong, but margin control requires attention. b. Technology category should be prioritized for expansion. c. Discount optimization is critical to protect profitability. d. Revenue concentration suggests focused inventory and marketing strategies. e. Negative-margin transactions must be monitored and controlled