I am an AI-powered Data Analyst and Junior Data Scientist passionate about turning raw data into meaningful business insights.
I work across data analysis, visualization, and machine learning basics, building real-world, end-to-end projects that mirror industry use cases.
Currently focused on becoming job-ready by strengthening fundamentals, project depth, and storytelling with data.

• 🐍 Python
• 🧮 Pandas
• 🔢 NumPy

• 📈 Matplotlib
• 🎨 Seaborn
• 🧩 Plotly

• 🧠 SQL
  • MySQL (Basics)
  • PostgreSQL (Basics)

• 🧹 Data Cleaning
• 🔬 Exploratory Data Analysis (EDA)
• 🧩 Feature Engineering (Basic)

• 📘 Supervised Learning
• 📊 Classification & Regression
• 🧪 Model Evaluation (Accuracy, Precision, Recall, ROC)
• ⚙️ Scikit-learn Basics

• 🔗 Git & GitHub
• 🌐 APIs (Basic usage)
• 📓 Jupyter Notebook
• 🖥️ VS Code
• 📊 Power BI (Beginner)

Problem:
Deliver real-time cricket insights in a clean, interactive dashboard.

Data:
Live / scraped match data (scores, teams, performance metrics)

Tools & Skills:
Python, APIs, EDA, Visualization, Dashboard Design

Outcome & Insights:

• Live match performance tracking
• Player & team trend analysis
• Interactive visuals for decision-making

Why it matters:
Simulates real-time analytics dashboards used in media & sports analytics.

Problem:
Analyze 10 years of e-commerce sales data to uncover trends and growth patterns.

What I did:

• Cleaned and prepared large datasets
• Performed in-depth EDA
• Built business-driven visualizations

Key Insights:

• Category-wise revenue growth
• Customer behavior trends
• Seasonal & long-term performance patterns

Tools:
Python, Pandas, Seaborn, Matplotlib, EDA

Why it matters:
Reflects real retail & business analytics problems.

Problem:
Detect fraudulent transactions using machine learning.

ML Approach:

• Data preprocessing & imbalance handling
• Feature selection
• Model training & evaluation

Algorithms Used:

• Logistic Regression
• Decision Tree
• Random Forest (basic)

Evaluation Metrics:
Accuracy, Precision, Recall, ROC-AUC

Why it matters:
A classic industry problem in fintech and risk analytics.

📌 Tip: Place GIF files in a /assets folder and link them here for faster loading.

• 📐 Statistics fundamentals
• 🎯 Probability basics
• ⚡ SQL query optimization
• 🔧 ML model tuning
• 🧠 Business problem framing
• 🗣️ Data storytelling & communication

• 💼 LinkedIn: [(https://www.linkedin.com/in/mdeva-datasci/)]
• 📧 Email: [email protected]

💡 Open to Data Analyst / Junior Data Scientist opportunities

⭐ If you like my work, consider starring my repositories — it really helps!