deepakgupta1/Scoring-Airbnb-Reviews

Score prediction in the categories of cleanliness, accuracy, check-in, communication, location, value (each out of 10) and overall (out of 100) based on the reviews left by customers on Airbnb.

12
/ 100
Experimental

Implements multi-stage feature engineering combining TF-IDF, CountVectorizer, and self-trained Word2Vec embeddings on cleaned review text, alongside sentiment analysis and target-encoded categorical features. Uses LightGBM regression with Bayesian hyperparameter optimization and 10-fold stratified cross-validation to handle the skewed rating distribution. Built with scikit-learn, NLTK, and Gensim on IBM Watson for cloud-based model training.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

6

Forks

Language

Jupyter Notebook

License

Last pushed

Jan 02, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/deepakgupta1/Scoring-Airbnb-Reviews"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.