Skip to content
View vishal-banshiwal's full-sized avatar
2 followers · 9 following

Block or report vishal-banshiwal

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
vishal-banshiwal/README.md

Vishal Banshiwal — Data Science Portfolio

Hi! I'm Vishal Banshiwal, a Data Scientist skilled in Python, Machine Learning, and Statistical Modeling. I specialize in building interpretable models for behavioral analytics, NLP, and time-series forecasting using TensorFlow, Scikit-learn, and XGBoost.

This repository contains selected projects demonstrating my end-to-end data science skills — from data cleaning and feature engineering to model validation and visualization.

📊 Featured Projects

🧠 Teen Smartphone Addiction Analysis & Prediction

  • Built a neural network model to predict addiction levels among teens.
  • Achieved R² = 0.95 | MAE = 0.20.
  • Insights could guide wellness initiatives. 🔗 View Project

🛍 Customer Segmentation using K-Means

  • Clustered mall customers into 4 groups.
  • Silhouette Score = 0.55.
  • Segments can help optimize marketing focus. 🔗 View Project

⚡ Hourly Energy Consumption Forecasting

  • XGBoost model for demand prediction.
  • RMSE = 3740.77 | MAPE ≈ 8.9%.
  • Forecasts can support energy planning. 🔗 View Project

💬 Sentiment Analysis on Airline Tweets

  • Processed 14k tweets using TF-IDF + Logistic Regression.
  • Achieved 80% accuracy | F1 = 0.78.
  • Insights could identify satisfaction drivers. 🔗 View Project

🧰 Tools & Libraries

Python • Pandas • NumPy • Scikit-learn • TensorFlow • XGBoost • Matplotlib • Seaborn • Power BI • NLTK

📬 Contact 📧 vishalbanshiwal8055@gmail.com
📍 Jaipur, India
LinkedIn | GitHub

Pinned Loading

  1. vishal-banshiwal vishal-banshiwal Public

    Config files for my GitHub profile.

  2. IITR-Capstone-Project IITR-Capstone-Project Public

    Jupyter Notebook

  3. Customer-Segmentation-KMeans Customer-Segmentation-KMeans Public

    K-Means clustering of mall customer data to identify spending patterns and uncover actionable customer segments.

    Jupyter Notebook

  4. Energy-Consumption-Forecasting-XGBoost Energy-Consumption-Forecasting-XGBoost Public

    XGBoost-based time-series model forecasting hourly energy demand using lag and calendar features — RMSE = 3740.77, MAPE ≈ 8.9%

    Jupyter Notebook

  5. Sentiment-Analysis-Airline-Tweets Sentiment-Analysis-Airline-Tweets Public

    NLP model classifying 14K airline tweets as positive, neutral, or negative using TF-IDF and Logistic Regression (Accuracy = 80%, F1 = 0.78).

    Jupyter Notebook