Portfolio

Repository containing portfolio of data science projects completed by me for academic, self learning, and hobby purposes. Presented in the form of iPython Notebooks, and R markdown files (published at RPubs).All the projects below are written in R also.

Note: Data used in the projects (accessed under data directory) is for demonstration purposes only.

Contents

• Machine Learning

• Unsupervise Learning

  • Credit Card Segmentation: Clustering of users on the basis of different variables using KMeans Unsupervised Learning.

• Supervised Learning

  • American Express ML Hackathon: Used XG boost for gradient boosting. Based of clickstream data, we have to predict if session will end in a adClick or not.
  • Telecom Churn Analysis: Analyze the reason for Churning out of customers. Classify the users on the basis of various matrices.
  • Bike Rental Prediction: Predict the number of bikes to be rented in the coming year to prepare the company for demand using various regression ML algorithms.
  • Marketing Campaign: : Extensive Data cleaning and wrangling. Classification of users whether they’ll revert to a particular campaign.

• Time Series

  • Walmart Sales Forecast: Extensive Data cleaning and wrangling. Classification of users whether they’ll revert to a particular campaign.
  • Employee Absenteeism: Analyze the reason for absenteeism. Multivariate TIme Series Problem to predict the number absenteeism next year

• Text Mining

  • Text Mining Sentiment Analysis: Using wordCloud to determine the frequency of words and then performing sentiment analysis.

Tools: scikit-learn, Pandas, Seaborn, Matplotlib, RandomForest,NLTK, XGBoost,