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,