Text-based Search Engine

(Java, Apache Lucene, API, SVM)

Published a large-scale, text-based search engine in Java leveraging Apache Lucene for 33,258 astronomical publications
Utilized machine learning functionality such as ranking diversification and learning-to-rank with an SVM classifier and integrated multiple information-retrieval models to analyze data for classification and regression analyses
Constructed a predictive model for document relevance based on Cornell SVM-Rank with 18 features which improved ranking precision by 20%