ENSIT Distinguished Talks Series: Recommender Systems Predictions

Prof. Olfa Nasraoui, Professor of Computer Engineering and Computer Science, Endowed Chair of e-commerce, and the founding director of the Knowledge Discovery and Web Mining Lab at the University of Louisville, USA.  provides a seminar, which is free and open to the public, about   understanding the Recommender Systems Predictions (Tell me Why? New Research in Building Recommender Systems that Can Explain their Predictions). This Talk was originally given by Prof. Nasraoui as an invited tech talk at Amazon headquarters in Seattle, WA, USA.

The seminar will take place in the A302 (Amphitheater A2)  at ENSIT on Friday, October 12, 2018 from 10.30 a.m.

Abstract :

At its core, Big Data is enabled by advanced Machine Learning (ML) models that are now being used increasingly to enable decision making in many sectors, ranging from e-commerce to health, education, justice, and criminal investigation. Hence, these algorithmic models are starting to directly interact with and affect the daily decisions of more and more human beings. In particular many models are black box models that make predictions without any justification to the user. Without any mechanism to allow humans to understand and question the reasons behind them, Black Box predictions lack justifiability and transparency. In addition, they cannot be scrutinized for possible mistakes and biases. Therefore, designing explainable machine learning models that facilitate conveying the reasoning behind their predictions, is of great importance. Yet, one main challenge in designing Big Data models is mitigating the trade-off between an explainable technique with moderate prediction accuracy and a more accurate technique with no explainable predictions.

This talk will focus on a special family of Machine Learning models, namely recommender systems; and will present our recent research in building explainability into a selection of state of the art Black Box recommender systems based on Matrix Factorization and Deep Learning.