We welcome Divyanshu Marwah for his Master thesis on TF-IDF variants for machine learning and recommender systems
Divyanshu Marwah is an MSc student at the School of Computer Science and Statistics at Trinity College Dublin. He is doing his post-graduate studies in computer science with a specialization in Data Science. Before joining the Master’s, he worked on data modeling, data integration, java development, and automation at Envestnet Yodlee in Bangalore, India. Divyanshu has also worked on text-based recommendation systems and text analytics at Paxcel Labs in Chandigarh, India.
Divyanshu’s research interests include machine learning, recommender systems, and text analytics. His dissertation topic is about improving recommendation effectiveness through novel variants of the TF-IDF weighting schemes. TF-IDF is one of the most popular term weighting algorithms used in information retrieval and recommendation engines. In his project, Divyanshu will be looking into ways to improve TF-IDF’s performance, starting with time normalized TF-IDF. He will be using Elasticsearch to index the dataset and use the custom scoring feature to test the algorithm.