Predicting the Users' Clickstreams Using Time Series Representation, Symbolic Sequences, and Deep Learning: Application on Job Offers Recommendation Tasks

Abstract

During the last decade, the expansion of automatic e-recruitment systems has led to the multiplication of web channels (job boards) that are dedicated to job offers disseminations. In a strategic and economic context where cost control is fundamental, the identification of the relevant job board for a given new job offers has become necessary. The purpose of this work is to present the recent results that we have obtained on a new job board recommendation system that is a decisionmaking tool intended to guide recruiters while they are posting a job on the Internet. First, the job applicant clickstreams history on various job boards are stored in a large learning database, and then represented as time series. Second, a deep neural network architecture is used to predict future values of the clicks on the job boards. Third, and in a parallel way, dimensionality reduction techniques are used to transform the clicks multivariate numerical time series into temporal symbolic sequences. Ngrams are then used to predict future symbols for each sequence. Finally, a list of top ranked job boards are kept by maximizing the clickstreams forecasting in both representations. Our experiments are tested on a real dataset, coming from a job-posting database of an industrial partner. The promising results have shown that using deep learning, the recommendation system outperforms standard multivariate models.