Yacine ASLIMI

As a Tech Lead Data at Transform-R, I am the main technical contact for clients, guiding them through the transition from SAS to R by identifying specific needs and proposing tailored technical solutions. • Conducted audits and diagnostics of existing environments, analyzing the conversion needs of current SAS scripts and evaluating performance for optimal migration to R. • Defined migration steps and monitored project timelines for successful conversion. • Designed and delivered specialized training sessions for client teams focused on data science and machine learning.

As an Analytics Engineer at Servier, I've worked on the building of an analytical data platform from scratch for researchers and data operators in France and around the world. The platform is equipped with a variety of tools such as Posit Workench (formerly R Studio Workbench), Posit Connect, Posit Package Manager, SAS Studio 9.4, Google Cloud Storage, and Big Query. I used DevOps tools such as Docker, Terraform, Github, and Gitlab to set up the platform. I am also responsible for converting SAS programs to R. I work in an international agile environment with developers based in France, Switzerland, and the United States, and I communicate in English with stakeholders. I also provide support and training to platform users on new features developed. To gather and express business needs, I use tools such as Confluence and Jira. I am also responsible for fixing bugs and adding new features in SAS and R programs. Additionally, I developed SAS, Python, and R programs, as well as Shiny applications to meet the needs of the pharmaceutical industry. In close collaboration with the teams responsible for clinical studies at Servier, I worked on ADaM, SDTM, and Stat files used in presenting studies to regulatory agencies such as the FDA. My role is to provide technical solutions for processing and analyzing clinical study data, as well as data visualization tools for end users.

The goal of this course was to provide Master's degree students with a comprehensive understanding of the key concepts and practical applications of Machine Learning and MLOps using Azure, as well as to equip them with the necessary skills to design, implement, and manage Machine Learning systems in a DevOps environment. Course 1: Introduction to Machine Learning Comparison between Machine Learning models and traditional software Overview of DevOps and Machine Learning workflows Using ML as combined code and data Different components of a Machine Learning system Quiz on Machine Learning fundamentals Supervised learning: Classification and Regression Setting up Azure DevOps environment Introduction to ML Studio Course 2: Getting started with Azure DevOps Managing data for MLOps Accessing, validating, and transforming data Data model construction Data and Machine Learning pipeline Modeling and training the model Model validation and deployment Making a trained model available in production Testing a Machine Learning system Orchestrating continuous delivery Course 3: Quiz on the previous session Model monitoring and data versioning management Application practical exercise Pair synthesis project.

Data Analyst training: - Introduction to data analysis with Python Pandas - Introduction to Machine Learning with Python Scikit-learn

Technical support on a mission to convert SAS scripts to R on behalf of INSEE. Subject: Program for calculating the Consumer Price Index (CPI) for fuels. SAS and R technical expert as part of the project to convert SAS programs to R technology on behalf of INSEE. The programs concern the calculation of the Consumer Price Index (CPI) for fuels. List of tasks associated with the mission: - Estimation of the rest to be done on the non-converted programs - Recommendation and technical design (which R package used, development methodology, tests, deployment, documentation) - Advice to businesses after technical feasibility study to convert certain SAS programs - Advice to the development team on working methodologies - Technical support to the development team for the choice of R packages and technical questions - Support for the development and conversion of SAS programs to R - Training and upskilling of the developer team on the new R packages to be used

I provided an introductory course on Data Science and Cloud Computing to Master 2 MIAGE students at the University of Paris Saclay. The course covered the following topics: Python programming language Google Cloud platform Data Scraping techniques The course aimed to introduce students to the fundamental concepts and tools of Data Science and Cloud Computing. In the Python module, the students learned the basics of programming, as well as how to use Python for Data Science tasks such as data cleaning, analysis, and visualization. In the Google Cloud module, the students learned about Cloud Computing, including Cloud storage, computing, and data processing services. Finally, in the Data Scraping module, the students learned how to extract data from various sources, such as web pages and APIs, using popular tools and libraries. Throughout the course, the students gained hands-on experience by working on real-world projects and exercises. By the end of the course, the students were equipped with the skills and knowledge necessary to begin applying Data Science and Cloud Computing concepts in their own work and research.

I provided a Data Science training course in Python to Master 2 DEV WEB students at H3 HITEMA school, which included the following modules: Data Analysis module with Python - 7 days (7 hours per day) Introduction to Machine Learning module - 5 days Introduction to Business Intelligence module - 2 days The course was designed to provide students with the knowledge and practical skills necessary to analyze large datasets, build predictive models, and create business intelligence solutions using Python. Throughout the training, we covered various Python libraries and frameworks commonly used in Data Science, such as Pandas, Scikit-learn, and NumPy. The students were also introduced to the basics of Machine Learning, including supervised and unsupervised learning, and learned how to apply various Machine Learning techniques using Python. By the end of the course, the students were able to understand the entire Data Science process, from data collection and cleaning to building and deploying predictive models, and were equipped with the tools to begin applying their skills in real-world projects.

Simplon is a training organization that offers digital training for learners in different professions, regardless of their background. As a trainer at Simplon since July 2019, my role has been to train data analysts and data scientists by setting up and leading courses to teach R, Python, SQL, and data analysis. I have extensive experience in data, which has allowed me to lead four promotions of 24 learners, in data analyst and data scientist roles. The courses are based on practical exercises and real data projects, allowing learners to gain hands-on experience in their future professions. The 7-month course includes training in R, SQL, Python, data analysis, and machine learning. I am proud to have conducted successful training sessions in Active Pedagogy and have contributed to the development of learners' knowledge and skills in the data industry. The training is based on practice. The exercises and concrete projects, on real data, allow learners to better understand the reality of their future profession. My solid experience in data allowed me to complete these 4 promotions of data analyst and data scientist. Here is a description of the training I was able to conduct: - Lead Trainer for the promotion of 24 Data Analysts from November to June 2020 in Elancourt (78) - Trainer for promotion of 24 Data Scientists from August to January 2020 in Ecouen in partnership with Microsoft - Trainer for promotion of 24 Data Analysts in August 2019 in Nanterre - Trainer for promotion of 24 Data Analysts in July 2019 in Elancourt (First data promotion in Elancourt) Training description: Session training of 24 learners in data analysis and data science professions on Python, R, and SQL (7-month course). Data Artisan - Data Analyst course: * R training * SQL training * Python training * Data analysis training Data IA -Data Scientist course: * R training * SQL training * Python training * Data analysis training * Machine Learning training

I worked as a Data Analyst within the CRM department at Celio. I created and improved scripts for calculating the main weekly, monthly, and yearly KPIs for the group. Technologies used: SQL Server Python R

Consulting with Adway Conseil: Milleis Bank is a new bank created following the acquisition of the Barclays France business by an investment fund. It has over 100,000 clients in France and around the world. My role was to identify customers with "high potential" based on their profile data (income, socio-professional category, assets, wealth, etc.). Value Added: I conducted data analysis (PCA, MCA, etc.) on banking data using SAS to establish profiles of customers who are most likely to become "high potential" clients. Achievements: • Data exploration using SAS • Creation of a summary table of data (Product, Client, ID, Family ID, KYC, Wealth, Controlled Assets...) • Statistical analysis of variables • Detection of outliers and abnormal values for each variable • Data cross-tabulation such as Age x Income, Income x Socio-professional category • Creation of new variables (Seniority...) • Data visualization Technical Environment: SAS, SQL

BNP Paribas Risk ORC Solution (7 months): The mission consists of the development of a risk control and risk assessment tool for Risk ORC Solution, an entity of the BNP Paribas Group. It follows a recommendation (warning) issued by the European Central Bank on the way in which the BNP's "Risk Control Self Assessment" (RCSA) were collected. Mission: Creation of the app for the capture and evaluation of Risk s Control Self Assessment Technical environment: Excel, VBA and SQL

Consulting with Adway Conseil: Creation and deployment of a tactical tool for recording controls and risk self-assessments (RCSAs) across all business units and entities of BNP in France and around the world, following a recommendation from the ECB. Value Added: Development of the application. Achievements: • Gathering and analysis of team requirements • Proposal and estimation of technical solutions • Design and development of the tactical tool in Excel/VBA for: Assessment of inherent risk based on historical incidents, near misses, potential incidents, external incidents, frequency of occurrence, and severity (amount) Implementation of Level of Control 1 (LoD1), Level of Control 2 (LoD2), recommendations, permanent control actions to reduce inherent risk Calculation of residual risk resulting from the implementation of controls Synthesis of all RCSAs by business unit and risk • Evolutionary maintenance of tools and user support • Presentation of the tool to various entities (CIB, ARVAL, Global Market...) in English • Preparation of tool documentation • Development of a compilation macro for all RCSAs to feed the target tool

Mission 1: CSA Data Consulting - HAVAS Group (One month) Marketing Project: Measure of the media contribution on the company turnover under SAS. SAS, VBA and Excel ------------------------------------------------------------------------------------------------------------------- Mission 2 : ORANGE - Intervention Unit Data mining and Machine Learning projects: • Forecast of the number of interventions for each of the territorial entities of Orange. • Creation of a decision support tool to anticipate the payment of penalties to third-party operators (non-Orange) in the event of a default on an unbundled line. Explanation: • Prediction of the ”volume” variable: Statistical and econometric models (Exponential smoothing, HoltWinters, ARIMA) with HiveQL, Python (Pandas, Scikit-learn), R (forecast) and Excel • Creation of a table of synthesis of the data under Hive including only the unbundled interventions (Wholesales) and prediction of ”Ranks” and ”Closing Code” variables using Random Forest Algorithm. (HiveQL and Python)

Consulting with Lincoln: As a data scientist within the intervention department of the Orange group, I carried out various missions involving data analysis and predictions. The first mission was to analyze data related to interventions carried out by Orange technicians (such as installation of live box, fiber optic cable, etc.) to determine the characteristics of those that did not end correctly. Then, I developed a machine learning algorithm in Python to predict these intervention failures. The second mission was to create a decision support tool to anticipate the payment of penalties to third-party operators (non-Orange) in case of a failure (anomaly) of a deregulated line. Finally, the last mission was about predicting the number of technicians (ETR) needed at Orange over the next 6, 12, and 18 months using time series approach. Examples of tasks carried out during these projects: • Gathering requirements from different departments • Statistical analysis and coherence table on technician closing data • Weekly queries and reporting on the number of technicians (ETR) who completed the technician survey using HiveQL • State of the art and documentation on querying Hive with Python • Presentation of this document to all DERS data miners in the Orange group (internal session) • Prediction of the "volume" variable: statistical and econometric models (exponential smoothing, HoltWinters, ARIMA, BATS) with HiveQL, Python (Pandas, Scikit-learn), R (forecast) and Excel • Prediction of the "Rank" and "Closing Code" variables using the Random Forest algorithm (HiveQL-Python) • Training Orange's Datamining teams (DESS) in a monthly webex on how to query the DataHub with Python (the goal was to bypass Hive/Hue) Technical Environment: R (tseries, forecast, ggplot2), Anaconda Python (Scikit learn, Pandas, numpy), Hive, Hue, PowerBI, VBA, HiveQL, SQL, Excel

Consulting with Lincoln: As a data scientist within the intervention department of the Orange group, I carried out various missions involving data analysis and predictions. The first mission was to analyze data related to interventions carried out by Orange technicians (such as installation of live box, fiber optic cable, etc.) to determine the characteristics of those that did not end correctly. Then, I developed a machine learning algorithm in Python to predict these intervention failures. The second mission was to create a decision support tool to anticipate the payment of penalties to third-party operators (non-Orange) in case of a failure (anomaly) of a deregulated line.

Had worked to London mainly in order to improve my skills in English. Skills developed: - Fluency in English - Autonomy - Leadership

I have made a final year internship of six months in Business & Decision. I was both researcher and a data scientist. On the research part, my mission was to measure the impact of the parametric variables on Machine Learning models. On the data scientist part, from data provided by a rugby club, I had to find the probability that a player would be injured during a match or during training. I have also made a "State of the art" on Blockchain technology and its applications (Bitcoins and more generally Crypto-currency) for the R&D department. I resumed some of these ideas in an article written for the Blog of the company. (French) Obtained results: • Have carried out a six-month research project including reading and synthesis of scientific papers and have written a 130-page research report. • Have developed a preprocessing algorithm in R, resulting from this state of the art to significantly improve the accuracy of a Machine learning algorithm. (Confidential) • Have allowed isolating the category of a rugby player who is most likely to be injured in a match or at training (Clustering). • Have carried out research on Blockchain technology and its applications on behalf of Business & Decision and have written an article that partially reproduces the results of this research for the blog of the company.