Shiwen XIA

Quantitative Researcher, Data Scientist

photo
Education
09/2018 - 08/2019
Master of Science (Cycle d'Ingénieur), ENSAE ParisTech, Paris Area, FRANCE
Major : Statistics and Machine Learning
09/2018 - 08/2019
Master of Sciences (Double Degree), Université Paris-Saclay (ENS Cachan), Paris Area, FRANCE
Major : Mathematics and Applications
Specialty : Mathematics, Vision, Machine Learning (MVA)
09/2015 - 08/2018
Master of Science (Cycle d'Ingénieur), Ecole Polytechnique, Paris Area, FRANCE
Major : Computer Science and Applied Mathematics
Specialty : Data Science
09/2011 - 06/2015
Bachelor of Science, Nanjing University, Nanjing, CHINA
Major : Physics
Experience
04/2019 - Present
Quantitative Researcher, Qube Research and Technologies, Paris Area, France
03/2018 - 08/2018
Data Scientist Intern, Société Générale, Paris Area, France
  • Data Scientist in the Squad of Machine Learning of the Artificial Intelligence Tribe
  • Research and implement a new ontology-driven term-based semantical word-embedding, which outperforms standard word-embeddings in some semantics-oridented Text Mining tasks
Key words: Natural Language Processing Ontology Text Mining
06/2017 - 09/2017
Data Scientist Intern, Saint-Gobain, Paris Area, France
  • Data Scientist in the IT support department
  • Implement and test a text topic detector with Latent Semantic Analysis topic modeling method, achieve an accuracy over 95% on a test dataset with texts of 4 topics
Key words: Natural Language Processing Machine Learning Topic Modeling
Projects
12/2017 - 03/2018
Using Recurrent Neural Networks for Anomaly Detection
  • Tutored by Professor Yanlei DIAO, CS Lab of Ecole Polytechnique (LIX)
  • Use LSTM model to predict the resources allocation state of a Hadoop cluster system according to its historical logs, then to detect anomalous behaviors by measuring the difference between the prediction and the real state value
  • Anomaly Detection and Explanation Discovery on Event Streams published in: BIRTE'18
Key words: RNN/LSTM Anomaly Detection
Technology Stack
Languages
Python, C#, Java etc.
Python
PyTorch, Tensorflow, Numpy, Pandas, Xarray, Scikit-learn, Matplotlib, etc.
Certificats
Kaggle
Porto Seguro's Safe Driver Prediction, Leaderboard top 9%
WSDM - KKBox's Churn Prediction Challenge, Leadboard top 7%
MOOC
TensorFlow in Practice Specialization, (deeplearning.ai)
Deep Learning Specialization, (deeplearning.ai)
Applied with Data Science with Python Specialization, (University of Michigan)
Neural Networks for Machine Learning, (University of Toronto)
Natural Language Processing, (National Research University HSE)
Machine Learning, (Stanford University)
Honors & Awards
09/2018
École Polytechnique Foundation/DMRI Scholarship, granted by the École Polytechnique Foundation
09/2015
France Excellence Scholarship, granted by the Embassy of France in China
06/2015
Excellent Graduate of Nanjing University, granted by Nanjing University
11/2014
Excellent Student Cadre of Nanjing University, granted by Nanjing University
11/2013
Excellent Student of Nanjing University, granted by Nanjing University
09/2011
Excellent Freshman of Nanjing University, granted by Nanjing University
Languages
Chinese
native proficiency
English
professional working proficiency
French
professional working proficiency