Imane Sami

Predictive Maintenance Data Analysis and Cost Prediction of Maintenance Contracts. As a Data Scientist/Data Analyst at Volvo, I specialized in extracting, preprocessing, and analyzing telematic data from clients, mechanics, and vehicles. My focus was on building failure probability prediction models for vehicle parts to optimize maintenance contract pricing strategies. Leveraging Python, Spark, and Microsoft Azure technologies such as Azure DataBricks and Azure Storage Explorer, I contributed to data-driven decision-making processes, driving operational efficiency and cost-effectiveness. Key responsibilities included: - Spearheaded the extraction and aggregation of telematic data from clients, mechanics, and vehicles, leveraging advanced tools and platforms such as Python, Spark, Microsoft Azure DataBricks, and Microsoft Azure Storage Explorer. - Conducted meticulous preprocessing and exploration of the aggregated data, ensuring its quality and relevance for subsequent analysis. - Utilized cutting-edge techniques to develop failure probability prediction models for various vehicle parts, aiming to optimize maintenance contract pricing strategies. - Employed Python and Spark for model development and implementation, harnessing the computational power of distributed computing to handle large-scale datasets efficiently. Leveraged Microsoft Azure DataBricks and Azure Storage Explorer for seamless data management and collaboration within the team. - Collaborated closely with stakeholders to understand business requirements and translate them into actionable insights, contributing to data-driven decision-making processes.

Developed a multi-functional system to streamline the extraction, visualization, analysis, machine learning, prediction, and interpretation of data sets, with a primary focus on enhancing marketing targeting strategies. This project, centered around E-marketing Levers Optimization and Proposing a Prediction Prototype for TekAcademy training sessions, aimed to integrate diverse functionalities crucial for effective data-driven decision-making. - Executed meticulous Data Scraping of LinkedIn profiles utilizing Python, Selenium, and auxiliary libraries such as Time, Parsel, CSV, and HTML, ensuring accurate and extensive data collection. - Leveraged advanced techniques in Data Storage, employing JSON files and NoSQL Database (MongoDB) to efficiently store and manage large datasets, ensuring scalability and flexibility. - Implemented rigorous Data Preprocessing methodologies, including handling missing values, encoding categorical data, performing feature scaling, and employing dimension reduction techniques, utilizing Python programming. - Applied Machine Learning algorithms for prediction tasks, utilizing techniques such as Unsupervised Learning, Clustering (including the Elbow Method and K-Means algorithm), and evaluation metrics like Mean Absolute Error, employing Python and Sklearn libraries. - Utilized Data Visualization techniques to elucidate insights from the data, particularly focusing on visualizing clusters using Python libraries such as Matplotlib and Seaborn. - Assessed the performance of Machine Learning models through comprehensive evaluation methodologies, ensuring the accuracy and reliability of predictions. - Conducted thorough Data Interpretation and Analysis to derive actionable insights, guiding strategic decision-making processes.

- Spearheaded the implementation of a Business Intelligence tool utilizing SQL Server, focusing on budget analysis to drive strategic decision-making. - Demonstrated proficiency in Business Analytics, leveraging advanced techniques to visualize and analyze data effectively. - Employed Data Warehousing methodologies, including Extract, Transform, Load (ETL) processes, within SQL Server environment to ensure data integrity and accessibility. - Leveraged Microsoft Power BI, a cloud-based suite of business analytics tools, to seamlessly connect to diverse data sources, visualize complex datasets, and perform in-depth analysis. - Introduced to Data Warehouse architecture, gaining insights into Data Warehouse Database, Data Marts, and the intricacies of sourcing, acquisition, cleanup, and transformation processes (ETL). - Developed a comprehensive understanding of Metadata management and its significance in data governance and analytics. - Explored various query tools including query and reporting tools, application development tools, data mining tools, and OLAP tools, enhancing proficiency in data analysis and reporting capabilities.

- Managed the "Olympic Banking System" database utilizing Oracle DB, ensuring seamless operation and data integrity. - Prepared comprehensive statistical reports on a daily, weekly, and monthly basis, providing valuable insights into banking operations and economic trends. - Skillfully manipulated the Olympic Banking System installed on the IBM AIX platform with Oracle Database, optimizing data processing efficiency. - Leveraged organizational databases for conducting banking operations and gathering competitive intelligence, contributing to informed decision-making on price stability and the Moroccan banking system. - Conducted in-depth economic studies to assess the country's economic landscape, facilitating the formulation of strategic policies. - Collaborated with the assigned team to accurately account for banking transactions and compile comprehensive statistical summaries, supporting informed decision-making processes.