Prediction of downloadable quality of photographs
- 1 minNortheastern University, Boston, MA. Datathon 2023
This project provides an application of data analysis and modeling to a real-world challenge. The dataset contains a diverse set of features that can be explored and analyzed to develop a comprehensive understanding of the factors that influence the popularity of a photograph. I used a variety of machine learning techniques to develop predictive models that can accurately forecast the lifetime download count of a photograph. The project focuses not only on achieving high accuracy in their models but also to consider factors such as interpretability and generalizability. A model that achieves high accuracy on the training set but performs poorly on unseen data is not considered a good model. The models developed were ensured that it can generalize well on unseen data while still being interpretable and easy to understand.
More contents, updates and results coming soon
Amoolya Srinivasa
Bioinformatics Programmer at NYU Langone Health