Data Tech June 3, 2025

From Rail to Real Estate: Award winning Tableau Dashboard

Developed a machine learning pipeline that fuses Natural Language Processing (NLP) with audio feature analysis to quantify the impact of lyrical themes on commercial music success.

Task

End-to-end data science lifecycle: from scraping and cleaning complex text data to building and evaluating predictive models (Random Forest, Gradient Boosting) to forecast song popularity

  • Role

    Data Scientist

  • Tech

    Python, Scikit-learn, LDA (Latent Dirichlet Allocation), Spotify API, Genius API, Pandas, NLTK

  • Status

    Completed

Open Project
Back