• 🔍 I'm a Data Analyst AND AI Engineer passionate about uncovering stories hidden in data
• 🐍 I work primarily with Python for data analysis, visualization & automation
• 📈 I love transforming raw data into actionable insights and beautiful dashboards
• 🌱 Always learning - currently exploring Machine Learning & Predictive Analytics
• 💬 Ask me about Python, Data Analysis, SQL, or Data Visualization
• 📫 Reach me at: palakshay071@gmail.com

A production-style Data Engineering workflow — from raw CSV ingestion through Python-based data cleaning, cloud database loading on AWS EC2, and advanced SQL analytics on a music streaming dataset.

• Goal: Build a complete data pipeline: ingest raw play data, clean it with Python & Pandas, load into cloud-hosted PostgreSQL, and extract insights using SQL joins, aggregations, and window functions.
• Tools: Python PostgreSQL AWS EC2 Pandas SQL
• Highlights: 14 raw records ingested → 10 clean records loaded to DB | 7 SQL queries written | 3 tables & 3 indexes created

A real-world business intelligence workflow — from raw data ingestion to executive-level dashboard reporting, covering data engineering, SQL analytics, KPIs, customer segmentation, and revenue forecasting.

• Dataset: 5,000 synthetic transactions | 30 products | 2,859 unique customers | May 2025 – May 2026
• Tools: Python PostgreSQL Power BI SQL ETL
• Highlights: Identified top-selling categories, low-performing months, and revenue concentration risks to drive strategic business decisions

Analyzed whether market sentiment — Fear, Neutral, or Greed — has a measurable impact on trader PnL, win rate, and trade size to extract actionable strategy insights from real trading data.

• Tools: Python Pandas Jupyter Power BI
• Highlights: Greed → higher PnL & win rate | Fear → higher losses & lower win rate | Large trades generate significantly higher returns

⭐️ If you find my work interesting, consider starring some repositories! ⭐️