This repo is a collection of example projects from students in General Assembly's part-time Data Science course. Rather than being a comprehensive collection of projects, its purpose is to give incoming GA Data Science students a sense of the variety and scope of past projects, and to spur their thinking for their own projects.
- Data Athletics: Analyzing Triathlete's Performance (athletics_presentation.pdf, code and data)
- Bike Sharing in Mexico City (bike_presentation.pdf, code)
- Predicting User Churn (churn_presentation.pdf)
- Predicting consumer disputes (disputes_presentation.pdf)
- Using Twitter Sentiment to Predict the NYC Mayoral Election (election_paper.pdf, election_presentation.pdf)
- Social media and brand marketing in the hotel industry (hotel_paper.pdf, hotel_presentation.pdf)
- Predicting Kickstarter (kickstarter_presentation.pdf, code)
- Predicting Loan Defaults in Peer-to-Peer Lending Markets (loans_paper.pdf, loans_presentation.pdf)
- Classifying PDFs as Likely Malicious or Likely Benign (malware_presentation.pdf)
- Twitter Music Recommendation Engine (music_presentation.pdf)
- Kaggle Learning Social Circles in Networks (networks_presentation.pdf)
- NPR One: App Store Reviews Text Analysis (npr_reviews_presentation.pdf)
- NPR One: Predicting User Behavior with N-Nearest Neighbor Stories (npr_stories_presentation.pdf)
- Can I use social media data to recommend countries to visit based on my travel history? (travel_paper.pdf, travel_presentation.pdf)
- Behance.net Image Analysis Project (paper, code)
- Building Predictive Models for NYC High Schools (paper)
- Kaggle Acquire Valued Shoppers Challenge (proposal, presentation, code)
- Kaggle Allstate Purchase Prediction Challenge (paper, presentation, code)
- Predicting Partisan Affiliation of Twitter Users (proposal, code)
- Using Data Science to Inform Business Investment Decisions (paper, presentation, code)
- Validating Crowdsourced Pricing (presentation, paper with code)