Mahadev Pandharpote

Hi, I'm Mahadev

Data Scientist | Python, SQL, Machine Learning, Power BI | Turning Data Into Actionable Insights

BTech in Computer Engineering

Contact Me View Resume

About Me

Transforming Data into Actionable Insights

   As a passionate and self-motivated data enthusiast, I have built a strong foundation in Python, SQL, Machine Learning, and Data Analysis. Through academic and personal projects, I’ve developed end-to-end solutions such as recommendation engines, real-time scream detection, and image classification models, showcasing my ability to work with both structured and unstructured data. I’ve also performed extensive EDA, data cleaning, visualization, and transformation—including IPL dataset analysis and Uber demand forecasting using Random Forest, Matplotlib, and Seaborn.


   I’m proficient with tools like Power BI, Flask, and have experience creating dashboards, feature engineering, anomaly detection, and converting raw data into actionable insights. I’m now seeking an opportunity as a Data Analyst or Data Scientist where I can apply my analytical mindset, technical skills, and problem-solving abilities to support data-driven decision-making and contribute to meaningful business impact.

Personal Details

Pune, Maharashtra, India

9356804873

pandmahadev120@gmail.com

Core Competencies

Python Programming

Proficient in Python for data analysis, machine learning, and statistical modeling.

  • Python for data science
  • Statistical analysis
  • Data preprocessing
  • Feature engineering

Power BI

Creating interactive dashboards and compelling data visualizations.

  • Data visualization
  • Interactive dashboards
  • Analytical problem-solving
  • DAX

SQL & Databases

Strong SQL skills for data extraction, manipulation, and database management.

  • SQL query optimization
  • Database management
  • Data extraction
  • Tools: MySQL, PostgreSQL

Machine Learning

Applying ML algorithms for predictive modeling and pattern recognition.

  • Supervised & unsupervised learning techniques
  • Classification, regression & clustering models
  • Feature engineering & data preprocessing
  • Model evaluation, tuning & validation
  • Predictive modeling, anomaly detection & demand forecasting

Deep Learning & NLP

Building deep learning models and NLP pipelines to extract insights from text and unstructured data.

  • Neural Networks (CNN, RNN – foundational), TensorFlow
  • Text preprocessing & tokenization
  • Word embeddings (Word2Vec, GloVe)
  • Sequence models (RNN, LSTM)
  • Transformer-based models (BERT)
  • Sentiment analysis & text classification

Tools & Data Skills

Proficient with modern development tools and core data analysis techniques used across data science and workflows.

  • Git & GitHub (version control)
  • Jupyter Notebook & VS Code
  • Pandas & NumPy for data manipulation
  • Exploratory Data Analysis (EDA)
  • Feature engineering & data preprocessing
  • MS Office (Excel, PowerPoint, Word)

Projects

Telecom Customer Churn Prediction

Role: Data Scientist / ML Engineer

  • Built an end-to-end ML system on 243,553 real telecom customer records
  • Engineered features: tenure, total usage, usage per dependent, age groups, smart city/pincode handling
  • Handled severe class imbalance using SMOTE
  • Trained XGBoost model achieving ROC-AUC 0.91
  • Added SHAP explanations to make every prediction interpretable
  • Developed & deployed a real-time interactive web app using Streamlit
  • Fully deployed and publicly accessible (anyone can test it live)

Tech: Python, Pandas, Scikit-learn, XGBoost, Imbalanced-learn, SHAP, Streamlit, GitHub, Streamlit Cloud

Live Demo GitHub

🏏 IPL Data Science Project

Role: Data Scientist

  • Cleaned & engineered IPL datasets for analysis.
  • Explored player performance, team efficiency, and match trends.
  • Built visualizations with Pandas, Matplotlib, Seaborn.
  • Implemented ML models for forecasting & prediction.

Tech: Python, Pandas, Seaborn, Matplotlib, Scikit-learn

GitHub

🚖 Uber Data Science Project

Role: Data Analyst / ML Engineer

  • Analyzed ride data for demand, peak hours, and geography.
  • Performed data cleaning, feature engineering & anomaly detection.
  • Created dashboards with Matplotlib & Seaborn.
  • Built Random Forest models for demand forecasting.

Tech: Python, Pandas, Seaborn, Matplotlib, Scikit-learn

GitHub

🎤 Scream Detection & Alert System

Role: AI Engineer / Full-Stack Developer

  • Built Flask app integrating audio processing + AI classification.
  • Trained TensorFlow model for scream detection.
  • Implemented 5-sec live audio capture & PostgreSQL storage.
  • Integrated WhatsApp API for real-time emergency alerts.

Tech: Python, Flask, TensorFlow, PostgreSQL, Twilio API

GitHub

⚽ European Soccer Data Analysis

Role: Data Analyst

  • Performed advanced SQL analysis on a large European soccer database.
  • Built CTE-based queries to evaluate team performance, points, and outcomes.
  • Analyzed player ratings, seasonal goal trends, and home vs away advantages.
  • Conducted Python-based correlation analysis between defensive pressure and goals conceded.
  • Designed interactive Power BI dashboards for insight visualization.

Tech: SQL (SQLite), Python (Pandas, SciPy), Power BI, Git/GitHub

GitHub

📊 Customer Segmentation & RFM Analysis

Role: Data Analyst

  • Performed end-to-end RFM (Recency, Frequency, Monetary) analysis to segment customers based on purchasing behavior.
  • Cleaned and transformed transactional data using Power Query and resolved data quality issues.
  • Designed a star schema data model with fact and dimension tables for scalable analytics.
  • Implemented percentile-based RFM scoring and classified customers into Champions, Loyal, At Risk, and Lost segments.
  • Built an interactive Power BI dashboard with KPIs, scatter plots, trends, and slicers for business insights.

Tech: Power BI, DAX, Power Query, Data Modeling, Git/GitHub

GitHub

🏢 HR Analytics: Employee Attrition Prediction

Role: Data Scientist / Data Analyst

  • Conducted end-to-end analysis on IBM HR dataset (1,470 employees) to predict employee turnover and identify key drivers.
  • Performed data cleaning, exploratory data analysis (EDA), and visualization to uncover patterns like overtime impact, long commutes, and low salary hikes.
  • Engineered features, encoded categoricals, and scaled data for modeling.
  • Trained and evaluated a Random Forest Classifier (~86–88% accuracy, strong ROC AUC) with feature importance analysis.
  • Deployed an interactive web app using Streamlit for real-time attrition risk predictions and EDA visualizations.

Tech: Python (Pandas, Scikit-learn, Matplotlib, Seaborn), Streamlit, Joblib, Git/GitHub

GitHub | Live Demo

Certificates

🐍 Python
🗄️ SQL
📊 Data Science
🤖 Machine Learning
📈 Power BI

Key Strengths

Analytical Skills

Strong ability to analyze complex datasets, identify patterns, and extract meaningful insights that drive decision-making.

Anomaly Detection

Expertise in identifying unusual patterns and outliers in data to prevent issues and optimize processes.

Demand Forecasting

Skilled in building predictive models to forecast future trends and support strategic planning initiatives.

Educational Background

Bachelor of Technology

Computer Engineering

Vilaarao Deshmukh Foundation Group of Institution , Latur 413512

Dr. Babasaheb Ambedkar Technological University, lonere

Nov 2021 - Oct 2025

7.5 CGPA

Summary: Focused on Computer Engineering with strong exposure to Artificial Intelligence, Machine Learning, Data Science, and Full-Stack Development. Built multiple real-world end-to-end projects that demonstrate problem-solving, data handling, and application development skills.

Academic & Personal Projects:

• Book Recommendation System (Collaborative Filtering, Flask)

• Movie Recommendation System (Content-Based Filtering)

• Scream Detection AI Application (Audio Classification, Flask, TensorFlow)

• Image Classification Project (CNN Model)

• College Website Development (Frontend + Backend)

• IPL Dataset Exploratory Data Analysis

• Power BI Dashboards & Data Transformation

Achievements:

Strong hands-on experience with Python, SQL, Machine Learning, and analytics tools

My Data Science Journey

1

Foundation Building

Developed strong programming skills in Python and SQL through coursework and self-study.

2

Specialization

Focused on machine learning, predictive modeling, and data visualization with Power BI.

3

Practical Application

Applied data science techniques through academic projects and personal initiatives.

4

Ready to Contribute

Seeking opportunities to apply skills and grow in professional data science roles.

What I Bring to Your Team

Real-World Problem Solving

Experience applying data science methods to tackle practical challenges through projects focused on analysis, visualization, and predictive modeling.

Continuous Learning

Always eager to learn new technologies, methodologies, and best practices in the rapidly evolving data science field.

Analytical Mindset

Strong critical thinking abilities combined with attention to detail to extract actionable insights from complex datasets.

Career Aspirations

Seeking Opportunities

I am actively seeking internship or entry-level positions in data science where I can further sharpen my skills and contribute meaningfully to innovative teams.

My goal is to work with organizations that value data-driven decision-making and provide opportunities for professional growth and skill development.


Get In Touch

My Goals

  • Contribute to data-driven decision making
  • Develop expertise in machine learning
  • Work on challenging real-world problems
  • Grow with an innovative team

Let's Connect

Email

pandmahadev120@gmail.com



Mail To

Phone

+919356804873

Available for calls and discussions about data science roles.

Call Me

LinkedIn

Connect with me professionally to stay updated on my journey.


View LinkedIn