Matala Touir

Last update: February ****

PERSONAL INFORMATION

SUMMARY

A highly competent Advanced data scientist with more than 5 years of experience developing a wide range of innovative applications like Devices Failure Detection, Maintenance Plans, OnStar Sentiment Analysis Model, and Customer support system. Ability to use (data) statistics, machine learning and deep learning for finding complex data patterns that drive meaningful impact on the business. I am looking for the opportunity to build a challenging career and apply my skills in an innovative and simplify process. I enjoy working in a team and communicating data-driven results.

QUALIFICATIONS

AWS technology: Data Lake, S3, EC2, Aurora, Athena, RDS, DynamoDB, Redshift, Amazon Analytics, ElasticSearch, CloudSearch, Kinesis, MXNet, Gluon, AWS SageMaker Studio, AutoPilot, Glue ETL, QuickSight, CloudFormation, CloudWatch, CloudTrial, Amazon Elastic Map Reduce (EMR)/Spark, etc.

Visualization: Tableau, Amazon QuickSight, SPSS, Python (Matplotlib, Seaborn), SAS, JMP, Minitab.

Programming languages: SAS, JMP, TensorFlow, Kea, PyTorch, Python (SciKit-Learn, Pandas, NumPy, SciPy), PySpark, Scala, R, SPSS, PL/SQL, Anaconda Navigator, Jupyter Notebook.

MLOps tools: Domino Data Lab, Anaconda Jupyter Notebook, AWS SageMaker Studio/Canvas./RStudio, Anaconda Navigator, CleanML, BigML, SAS Viya.

Structured Database: Oracle, SQL server, MySQL, PostgreSQL

Unstructured Database: Semantic Object Models (SDM), MySQL, PostgreSQL, HBase, Cassandra, MongoDB, DynamoDB, Databricks, etc…

Big Data: Hadoop, MapReduce, Spark, Scala, Databricks, Kafka, Storm, Splunk, TensorFlow, Hive, Pig, Sqoop, Python, Impala, Cloudera Management, SparkML, etc.…

ML/DL Algorithms: Principal Component Analysis, Linear/Logistic Regression, Support Vector Machine, Clustering, Decision Tree, Naive Bayes, KNN (K-Nearest Neighbors), K-Means, Random Forest, Dimensionality Reduction Algorithms, Gradient Boosting & AdaBoost and NLP/AI (CNN, DNN, ANN)

Container Orchestration System. Nvidia GPU, Docker, and Kubernetes or other.

SAS Programmer Associate Certified.

Python Programming – Associate Certified

AWS Solutions Architect - Associate Certified

SAS Business Analyst Certification (in progress)

AWS ML and DL certification (in progress)

PROFESSIONAL EXPERIENCES

Georgia Pacific 01/2022 – Present

Data Scientist

Machine Learning and Deep learning modeling to ensure Dryer/Digester/Single Facer/ high quality product. Using data coming from thousands of sensors all over GP regions and factories. Models XGBoost, LightLGB and LSTM. Using SAS Viya, Python, and AWS SageMaker.

Computer vison programming models to classify / identify issues such as overheating and vibration. XGBoost and Neural Network. TensorFlow and keras.

Utilize advanced statistical/AI techniques to create high-performing predictive models to gather, define, and execute insights for effective optimization and decision making

Assure compliance with regulatory and privacy requirements during design and implementation of modeling and analysis projects.

Follow industry trends and historical data in insurance to identify AI processes and business improvement

Verify the performance of algorithms and predictive models based on experimental designs

Collaborate with multiple data-driven teams to ensure project initiatives are met for key stakeholders

Honeywell Corp 10/2020 – 12/2021

Advanced Data Scientist

Engage with business partners and team members to understand their challenges and translate them into data science solutions.

Coordinate data science and data engineering resources to achieve business goals.

Lead, supply, and provide thought leadership on the end-to-end development and deployment of predictive and prescriptive models for marketing, sales, finance, supply chain, and other business applications.

Explore large datasets using modeling, analysis, and visualization techniques. Transform the results into insights and recommendations.

Deliver presentations to senior business stakeholders that tell a cohesive and logical story using data.

Budget forecasting for all Honeywell organization using univariate/multivariate models: ML/DL models: SARIMA, SARIMAX, Prophet, LSTM, XGBoost, HOLTS, LightLGB, and Auto_XGB.

Using Natural Language Processing (NLP) to improve Honeywell’s NLP products and create new NLP applications. NLP responsibilities include transforming natural language data into useful features using NLP techniques to feed classification algorithms (CNN, ANN, DNN, etc…)

Participated with the Scrum team-- Scala development and testing of OEM, Enricher, Algorithm Executors.

Transformed natural language data into useful features using NLP techniques to feed classification algorithms.

General Motors 03/2017 – 11/02/2020

Data Scientist

Analyzed business critical data and recommended improvements.

Worked with large data sets consisting of predominantly images and conducted advanced analytics tasks. Assessed the effectiveness and accuracy of new data sources and data gathering techniques.

Worked with stakeholders throughout the organization to identified opportunities for leveraging company data to drive business solutions.

Developed custom data models and algorithms to apply to data sets.

Coordinated with different functional teams to implement models and monitored outcomes.

Developed processes and tools to monitor and analyze model performance and data accuracy.

Advised developers and engineers on latest data analytics technologies and assisted the team in process matters as related to development/support and provides the necessary on the job training and development of associates/contractors within the team.

Advanced data scientist with Natural Language Processing (NLP) to improve our NLP products and create new NLP applications. NLP responsibilities include transforming natural language data into useful features using NLP techniques to feed classification algorithms (CNN, ANN, DNN, etc…)

Used Natural Language Processing (NLP) and AI that enabled as to unlock unstructured data contained in NoSQL databases, documents, social media, and IoT (GM’s OnStar).

Used NLP to map out safety data and driver’s program data concepts and associated values and used this information for decision-making and analytics.

Used NLP to empower GM’s with specific applications and use cases such as:

oDocument profiling and classification (Predicted Truck prices and likeability using Sentiment Analysis and ML.

oTrucks’ price profiling and characterization

oImproving completeness or accuracy of GM’s OnStar documentation

osafety data and driver’s program data concepts extraction and mining using various data visualization and statistical methods.

oProblem list extraction and risk stratification/Computer-assisted coding using Python

oExtraction of data for predictive/inference quality measures

Identified factors that predict which truck will have the best performance and which will benefit from as well as comparing them with competitions using machine learning.

Designed models to predict devices' failures and set the appropriate maintenance plans.

Worked with GM’s Customer Care & Aftersales (CCA) business facing analytic groups to analyze, extract, normalize, and label relevant data, and operationalized ML and DL models after they are prototyped (Big Data, IoT, OnStar).

Created models for After Sales Customers services to optimize returning goods and price forecasting for GM’s trucks (GMC and Chevrolet).

Involved in the continuous enhancements and finding the best solution.

Wrote very complex SQL queries and designed reports using Tableau and AWS QuickSight

Data Scientist Manager 06/2014 – 02/2017

Help set and execute the vision for AI at GM and drive a culture of applied innovation

Manage group of data scientists, Scala developers, Databricks Admin as well as manage multiple projects concurrently.

Work closely with data engineers to build scalable AI solutions that drive business value for our business units and external customers

Work cross-functionally with other IT managers to implement models in production environment

Proven strong organizational and leadership skills (train junior data scientists and lead new college hire and internship program)

Collaborate with various departments to identify opportunities for process improvement and developing analytics use-cases.

Deliver advanced machine learning models to provide insights within the organization that lead to fact-based decision making.

Effectively utilize appropriate statistical, Machine Learning, Deep Learning, and Computer Vision models and techniques to solve various business problems.

Deliver many Delta Lake and AI / ML related project management and delivery expertise.

Implement ML / DL projects using data management and visualization techniques.

Manage very large solutions / framework for data extraction / data mining/ data wrangling and ensured data quality and integrity in the projects

Involve in the continuous enhancements and finding the best solution (performance testing of data-driven products)

Communicate results to colleagues, business partners, and senior management.

Visualize data and create reports (Tableau, SAS, QuickSigh).

MYASAP Consulting Group.

Project for the State of Georgia 10/2012 – 06/2014

Data migration specialist

Lead the government data migration imitative: Used Oracle SQL server databases and WebLogic as webserver.

Project Management using the most popular life cycle Agile method

Manage very large solutions / framework for data extraction / data mining/ data wrangling and ensured data quality and integrity in the projects.

Manage group of developers and database admins as well as manage multiple projects concurrently.

COX Communications 08/2007 – 09/2012

IT Manager & Data Architect

Developed business process to measure the company growth and measure the performance of the 24/7 on call support system.

Managed/coordinated IT teams to conduct the data migration (OS servers, Storage devices, Disaster Recovery strategy, and Network devices). Project Cost: 15$Millions.

Project Management using the most popular life cycle Agile method.

Coordinated with the stakeholders on project progress.

EDUCATION

Ph.D. Philosophy Doctor in Information System

North Central University, Arizona, USA.

M. Sc. Master of Science in Applied Statistics

Kennesaw State University, Georgia, Atlanta, USA.

M. Sc. Master of Science in Information System

Kennesaw State University, Georgia, Atlanta, USA.

Email: advyk5@r.postjobfree.com

Phone: 404-***-****

Address: 515 Warwick Pl., GA 30076

Linkedin: linkedin.com/in/matala.touir

Contact this candidate