Machine learning model used for link prediction. Goal of the project is to predict links between authors to check if a paper cites another paper or not. Project was carried out in the form of a Machine Learning competition on Kaggle.
Link prediction is the problem of predicting the existence of a link between two entities in a network.
The problem of link prediction has recently attracted a lot of attention in many domains. For instance, in social networks, one may be interested in predicting friendship links among users, while in biology, predicting interactions between genes and proteins is of paramount importance.
In this challenge, you will deal with the problem of predicting whether a research paper cites another research paper. More specifically, you are given a citation network consisting of several thousands of research papers, along with their abstracts and their list of authors. The pipeline that is typically followed to deal with the problem is similar to the one applied in any classification problem; the goal is to use edge information to learn the parameters of a classifier and then to use the classifier to predict whether two nodes are linked by an edge or not.