OBJECTIVE:

Seeking a position where I could implement skills and experiences that I have gained through education, training and experience to uncover insights, make accurate predictions, recommendations, improvements, and products that will guarantee organization success while learning new experiences.

TECHNICAL SKILLS:

• Oracle SQL Developer, SPARQL, web Protégé, OWL/RDF, GATE
• Oracle DB, IBM DB2
• Teradata
• Power BI, Tableau
• Semantic Web/Onto
• RESTful API, NLP, Cloud Computing, H2O
• Apache Spark
• Scikit Learn, Panda, Numpy, TensorFlow, SciPy, NLTK, Matplotlib
• R studio & Shiny
• Python, SAS, Java
• Text mining
• Machine Learning, Big Data
• Prescriptive Analytics
• Agile Project Management
• Predictive Analytic

PROFESSIONAL EXPERIENCE:

Data Scientist III

Confidential, IL

• Cost analysis, Transportation Freight Logistic Spend Optimization, Transportation Mode maximization, Supplier - Carrier Performance metrics, Predictive recommendation modeling.
• Lead Analysis, Data cleaning, wrangling and insight derivation, Quality data management ( Teradata, Oracle, DB2, Snowflake), Cost & Pass due Prediction, Report visualization and dashboarding (Power BI & Tableau) and Prescriptive analytics

Senior Software Engineer

Confidential, NC

• Actively Participate in Software requirement and Model based software design & Simulation review for Autosar Compliant Software Product Development for Vehicles.
• Researching Machine learning algorithm for Software testing &Manage MIL Software Testing and Jenkins Integration Testing data.
• Developed R Shiny dashboard UI to monitored anomaly in spending & part usage with statistical process control using, SVM, KNN, logistic regression, decision trees) and quantify uncertainty.
• Implemented PCA, Clustering, Elastic nets, bagging, boosting, L1 & L2 regularization, K-cross validation, grid search to optimize model predictive accuracy
• Performed exploratory data analysis on vehicle CAN data, model and create machine learning model to classify feature activity and predict system behavior on new model implementation
• Developed Test plans, test scripts for MATLAB Simulink MBSD to exposed defects and assurance quality.
• Reviewed and Analyzed Test report and extend test cases & scripts to MC/DC coverage
• Implemented Test driven development, boundary value analysis and partitioning to assurance confidence in software product quality

Data Scientist

Confidential, NC

• Acquired, cleaned structure and unstructured data from multiple sources and maintained Graph databases systems using text mining, natural language processing and semantic web using SPARQL, RDF/OWL and knowledge graph.
• Led analytics team to robust performance measure for customers and retailers using data envelopment analysis and Operation research leveraging on linear programming
• Managed and coached Data Analyst on data quality management and data profile
• Performed data curation for chatbot and augment search system development.
• Constructed machine learning algorithms in R to perform data exploration, data cleaning, modeling, pattern matching and quantify uncertainty.
• Participated in Software development, Inspection and testing (UI, webservices with REST API), defect tracking, and deployment to production a service on Microsoft Azure.
• Developed predictive model for churn and customer propensity analysis. Optimized predictive model algorithm, augmented search engine, relevance and recommendation.
• Developed data visualization with R shiny and generated executive summary reports from R studio. Participated in Software development, testing (webservices with REST API python scripts) and deployment to production.
• Architect and managed ontology data model, semantic meta data enrichment, annotation and domain specific topics and vocabularies (SKOS, Dbpedia, FOAF) Information extraction and retrieval from multisource and triplestore

Manager

Confidential, NC

• Implemented natural language processing and text mining to analyze and extract key feature from work order request to develop fault ontology knowledge base.
• Developed machine learning algorithm and trained Model to analyze and predict machine failure and make recommendation using prescriptive analytics and Optimization techniques
• Implemented SPARQL queries to enhance data quality, finding data, clean, remodeled and linked data.
• Performed failure mode effect analysis, fault tree analysis and maintained FRACAS report to extend and enrich Fault ontology for repair recommendation.
• Developed R Shiny dashboard UI to monitored anomaly in spending & part usage with statistical process control using, SVM, KNN, logistic regression, decision trees) and quantify uncertainty.
• Led, managed, coached and assigned tasks to data scientists and engineers
• Managed sprint planning and developed standard procedures to streamline and improve work processes for agile analytics team

Data Quality & Automation Analyst

Confidential

• Championed defects root cause analysis, corrective and preventive actions through clustering and principal component analysis and exploratory data analysis using R and Minitab.
• Developed dashboard to track quality metrics, documented defects, nonconformance, and process anomaly using statistical process control.
• Mined, analyzed and profile quality data.Cleaned & wrangled data from in process parameter
• Designed data driven solution to test results with analysis hypothesis testing and DOE
• Championed risk management using predictive analytics and continuous process improvement effort.

Reliability Data Analyst & Quality Engineer

Confidential

• Analyzed reliability time series data with R to predict failure modes.
• Analyzed warranty data and performed root cause analysis for, failure reporting and corrective action recommendation. Developed and design experiment based on warranty field data, developed and test hypothesis.
• Performed risk assessment forecast and developed mitigation plan.
• Performed accelerated testing, FMEA and Implemented Weibull software and statistical methods for life data and warranty analysis.