As a part of my PhD., I am developing large scale recommender sytems leveraging implicit feedback. To this end, I have been working under the supervision of Prof. Massih-Reza Amini and co-supervision of Post. Doc. Charlotte Laclau in order to apply deep learning methods to improve top-k recommendations on implicit feedback. More details about this work are here: Representation Learning and Pairwise Ranking for Implicit Feedback in Recommendation Systems. Additionally, we contributed a dataset consisting of click logs of users of Kelkoo for recommender system community after setting benchmark results for RecSys baselines meant for implicit feedback on the above mentioned dataset. More details about this work are here: KASANDR. Also, I have been working in collaboration with engineers at Kelkoo and Purch on the project Calypso where the objective is to recommend offers which interests a given user. Currently, we have been making efforts for putting Field-Aware Factorization Machines (FFM) and feature engineering in production. I Attended RecSys 2016 held in Boston and RecSys Summer School 2017 held in Bolzano where I became acquainted with leading people in RecSys community. Finally, I developed novel topic modelling techniques to monitor health using Twitter over time. Details of this work are here: Health Monitoring on social media over time
In this six month internship, under Dr. Sihem Amer-Yahia, I developed a simple yet effective topic modelling technique to predict future health topics being discussed in twitter, given the present health topics. More details about this work are present in this work: Health Monitoring on social media over time
In this 4 month internship with Dr. Sihem Amer-Yahia, I Worked in collaboration with computer scientists and geographers in the context of the CNRS MASTODONS CrowdHealth project where I developed a database indexing module in Postgres to optimize tweets extraction in real time and a tweet annotation module based on crowdhealth crowdsourcing. Then, I used an SVM classifier module based on a 10-fold cross validation to classify tweets into health and non health. Then, a topic model for inferring health information via sophisticated bayesian modelling.
Here, I studied and wrote jobs for filtered and wrapper based feature selection methods such as Information gain, Chi-Square, Principal Component analysis and forward feature selection algorithm (in java).
Here, I was responsible for configuration, monitoring, trouble shooting of Mail Server, providing support for Nokia Siemens Networks users, configuration monitoring and troubleshooting of FTP and managing clients helpdesk for telephonic and mail Support.
Here, I worked on ASP.NET infrastructure, learned in's and out's of visual studio , obtained familiarity with common language run-time and just-in-time compilation and Worked on MySQL on backend
Doctor of Philosophy (Ph.D.) in Recommender Systems and Online Advertising
Master's of Technology in Computer Science and Engineering
Bachelor's of Technology in Information Technology