En poursuivant votre navigation sur ce site, vous acceptez le dépôt de cookies dans votre navigateur. (En savoir plus)
Portail > Offres > Offre UMR7501-DELSCH-005 - Chercheur post-doctoral en science des données H/F

Post-doctoral researcher in data science M / F

This offer is available in the following languages:
Français - Anglais

Date Limite Candidature : jeudi 28 janvier 2021

Assurez-vous que votre profil candidat soit correctement renseigné avant de postuler. Les informations de votre profil complètent celles associées à chaque candidature. Afin d’augmenter votre visibilité sur notre Portail Emploi et ainsi permettre aux recruteurs de consulter votre profil candidat, vous avez la possibilité de déposer votre CV dans notre CVThèque en un clic !

Faites connaître cette offre !

General information

Reference : UMR7501-DELSCH-005
Workplace : STRASBOURG
Date of publication : Thursday, December 17, 2020
Type of Contract : FTC Scientist
Contract Period : 12 months
Expected date of employment : 1 March 2021
Proportion of work : Full time
Remuneration : from 2675.28 euros gross monthly according to experience
Desired level of education : 5-year university degree
Experience required : Indifferent

Missions

As an intern at IRMA, UMR university of Strasbourg et CNRS 7501, the post-doctoral researcher will carry out research work on the theme of artificial intelligence and data science. This research project is part of a research collaboration between the innovative young company Your Data Consulting (YDC) and two professors and researchers, Frédéric Bertrand (European university of technology) and Myriam Maumy-Bertrand (European university of technology, internship at IRMA).

Activities

Main activities:
Your Data Consulting is the owner of the LiveJourney SaaS platform, which can be found at https://www.livejourney.com. This platform enables mail order companies, manufacturing or delivery companies to dynamically view and analyze the journeys of their customers, products and packages. In addition, it allows companies to anticipate events that could slow down the process and detect bottlenecks. Several research themes have been selected for post-doctoral research.

ROOT CAUSE ANALYSIS (RCA) :
In software engineering, RCA is a problem-solving method used to identify the root causes of process failures [1]. It is widely used in computer operations, telecommunications, industrial process control, accident analysis (e.g. in aviation, rail transport or nuclear power plants), medicine (for medical diagnosis), the health sector (e.g. in epidemiology), etc. [2]. RCA clearly links to theoretical studies in causality, a new and promising area in statistical research, whose number of publications has been growing steadily since the 2010's [5, 2].
PROCESS PREDICTION
Process mining is a research discipline that uses artificial intelligence and data mining techniques on the one hand, and process modelling and analysis on the other. It facilitates the analysis of business processes on the basis of event logs extracted from computer systems, see the article in [7]. This is somewhat comparable to data mining, but the focus is mainly on the acquisition of process knowledge, see the article in [6]. Existing approaches allow to discover the process model, to detect changes in the initially designed model, to find correlations between process data and different variants of the model (see the article in [3]), to analyze and predict inefficient aspects (see the article in [4]).

CAUSALITY AND AI
Causality is a well-known problem in statistics and plays an important role in explanation, prediction and automated decision making [8]. Recently, with the rapid accumulation of massive data, it has become increasingly desirable to extract causal relationships from these data.

Valorization of results through scientific publications in the form of patents, papers in world leading conferences or articles in world leading journals.


References

[1] A. Abubakar, P. B. Zadeh, H. Janicke, and R. Howley. Root cause analysis (rca) as a preliminary tool into the investigation of identity theft. In 2016 International Conference On Cyber Security And Protection Of Digital Services (Cyber Security), pages 1–5, June 2016.

[2] Léon Bottou, Jonas Peters, Joaquin Qui nonero Candela, Denis X. Charles, D. Max Chickering, Elon Portugaly, Dipankar Ray, Patrice Simard, and Ed Snelson. Counterfactual reasoning and learning systems: The example of computational advertising. Journal of Machine Learning Research, 14:3207–3260, 2013.

[3] Pavlos Delias, Daniela Grigori, Mohamed Lamine Mouhoub, and Alexis Tsoukias. Discovering characteristics that affect process control flow. In Lecture Notes in Business Information Processing, volume 221, pages 51–63. Springer, Cham, 2015.

[4] Daniela Grigori, Fabio Casati, Malu Castellanos, Umeshwar Dayal, Mehmet Sayal, and Ming Chien Shan. Business Process Intelligence. Computers in Industry, 53(3):321–343, apr 2004.

[5] Judea Pearl and Dana Mackenzie. The Book of Why: The New Science of Cause and Effect. Basic Books, Inc., New York, NY, USA, 1st edition, 2018.

[6] Wil M.P. van der Aalst, Wei Zhe Low, Moe T. Wynn, and Arthur H.M. ter Hofstede. Change your history: Learning from event logs to improve processes. In 2015 IEEE 19th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pages 7–12. IEEE, may 2015.

[7] W.M. Van Der Aalst, Arya Adriansyah, Ana Karla Alves De Medeiros, Franco Arcieri, Thomas Baier, Tobias Blickle, Jagadeesh Chandra Bose, Peter Van Den Brand, Ronald Brandtjen, Joos Buijs, and Others. Process mining manifesto. In International Conference on Business Process Management, pages 169–194. Springer, 2011.
[8] Kun Zhang, Bernhard Schölkopf, Peter Spirtes, and Clark Glymour. Learning causality and causality related learning: some recent progress. National Science Review, 5(1):26–29, 11 2017.

Occasional activities:

Participate in the integration of research results into the LiveJourney platform hosted on AWS.

Participate in the analysis of real data sets in collaboration with the experts at Your Data consulting.

Skills

Position level:
Research Engineer in charge of post-doctoral research. A Ph.D. in a discipline related to data sciences is required.

Professional skills:

- General, theoretical or disciplinary knowledge
Knowledge of statistical or machine learning is essential. A good aptitude and appetence for programming is required. Knowledge of stochastic models and time series analysis would be appreciated. Experience with Petri nets will be valued.

- Knowledge about the work environment
A desire to be part of a research team at the frontier between academic research and applied research in companies.

- Operational know-how
Strong programming experience in one of the major languages of data science: R or Python. Experience in C, C++ or fortran, as well as in Pytorch, will be appreciated.

- Language skills
English: read, written and spoken.

Work Context

The position is located at the Institute for Research in Advanced Mathematics IRMA UMR7501 which is under the joint supervision of the CNRS and the University of Strasbourg.

Constraints and risks

Frequent meetings with YourData Consulting, a company located in Paris, are required. Visiting Your Data on a regular basis will be scheduled (2 times by month).

We talk about it on Twitter!