What About Your Next Job? Predicting Professional Career Trajectory Using Neural Networks

Accurate and effective analysis of professional career trajectories can help job seekers make the right job switch quickly. However, it is a non-trivial task to develop an effective model to predict the next job of users. Previous works either focus on feature engineering that resulted in heavy computations or not supporting complete solutions from the perspective of individuals. To this end, we propose an end-to-end model to predict the next job of users comprehensively. The problem of predicting the next job is broken into three tasks, i.e., position name prediction, salary level prediction, company size prediction. These three tasks share the same framework of the model with different output dimensions. Specifically, we reorder the raw features and regard each resume as a textual sentence consists of several key phrases. Word2Vec is utilized to train the hidden vectors of all phrases in the sentences. Followed by a feature extracting component comprised of a convolutional neural network (CNN) or a long short-term memory (LSTM) network. Experiments on a real-world dataset validate that our proposed model significantly outperforms baselines and reveal interesting insights into job transitions from two perspectives.