Experience

GDIT LTD

• United Kingdom
• IT Services and IT Consulting
• 1 - 100 Employee

• Data Scientist

  • Sep 2021 - Present

  In my role, I was responsible for various stages of data management and machine learning projects. This involved tasks like gathering and cleaning data, creating models, validating them, and presenting insights through visualizations. I used Python tools like Pandas, NumPy, Seaborn, and Scikit-learn to build machine learning models including Logistic Regression, KNN, and Gradient Boosting. I also focused on data privacy compliance by developing procedures in AzureSQL Database to identify and secure sensitive information. My work extended to utilizing Azure services through AzureSDK, such as AzureStorage and Azure Service Bus. I was also proficient in Big Data tools like Azure Databricks and Azure Data Lake Storage. I integrated data from various sources, for instance, HBO consumer subscription data from AzureServiceBus into Azure SQL Database and Azure PostgreSQL tables. My expertise encompassed a range of machine learning algorithms, addressing data imbalances, and generating automated reports. I also delved into natural language processing (NLP) for document classification and text summarization. Furthermore, I developed machine learning models using recurrent neural networks (LSTM) for time series analysis. Throughout the entire machine learning process, from data collection to model deployment, I utilized Python tools like Scikit-learn, NumPy, Pandas, Matplotlib, and Seaborn for thorough data analysis. My work extended beyond coding to include scripting, API integration, and collaborative efforts to maintain comprehensive reports. Show less



AbbVie

• United States
• Pharmaceutical Manufacturing
• 700 & Above Employee

• Data Scientist

  • Oct 2018 - Aug 2021

  In my project role, I adeptly managed data and employed machine learning techniques. This included executing SQL scripts for data validation across applications and conducting extensive data analysis using Python for migration, cleansing, transformation, and integration. Machine learning was a cornerstone of my role, focusing on regression and classification to predict outcomes and extract insights. I excelled in normalizing tables and establishing efficient relational schemas, boosting data structure effectiveness. Skilled in Excel and coding, I derived insights from diverse data using tools like VLookup and formulas. Beyond coding, I actively engaged in unit testing, providing valuable feedback for quality assurance. In the realm of Big Data, I showcased competence in Apache Spark and Kafka for robust data processing, extending to various Hadoop ecosystem components. Machine learning prowess translated to extracting structured insights from unstructured data. A standout achievement was crafting accurate logistic regression models in R and Python, effectively predicting subscription response rates based on diverse variables. I collaborated closely with business teams, translating requirements into actionable insights via reports and dashboards. My expertise spanned logical and physical data modeling, enhancing efficiency in ER and Dimensional Models. Proficiency in Python and Spark enabled me to implement diverse machine learning algorithms across projects. Automation skills came to the fore via COSMOS, Azure Data Factory pipelines, and PowerShell scripting, streamlining model refresh and boosting efficiency. My skill set extended to data transformation, SQL optimization, and Git repository management. Beyond technical proficiency, my collaborative spirit was a key driver in project success. Show less



Cummins Inc.

• United States
• Motor Vehicle Manufacturing
• 700 & Above Employee

• Data Scientist

  • Jul 2016 - Sep 2018

  In my role, I proficiently utilized Python for predictive machine learning, simulation, and statistical modeling. Data analysis was a forte, generating comprehensive reports via SQL queries from databases. AWS tools, like CloudWatch, CloudTrail, and SNS, established efficient monitoring for EC2 hosts. Proficient in data manipulation, preparation, normalization, and predictive modeling, I heightened efficiency and accuracy. AWS Lambda streamlined data transformation, refining data quality and ingestion. Tableau was pivotal for insightful reports and visualizations. My proficiency spanned Spark, Scala, Hadoop, HBase, Kafka, Spark Streaming, MLlib, and Python, enabling versatile machine learning application. A solid foundation from a Data Analytics boot camp underpinned my skills. Complex SQL tasks—queries, procedures, views, reports—in Microsoft SQL Server were adeptly managed. Designing, developing, and deploying AWS-based machine learning models was a hallmark. Algorithms like KNN, Decision Trees, Naïve Bayes, Logistic Regression, SVM, and Latent Factor Models were my expertise. Python's pandas and NumPy enabled seamless data preprocessing, complemented by seaborn, SciPy, and matplotlib. Data modeling tools like Erwin, Power Designer, and ER Studio amplified my ability to integrate Machine Learning, Predictive Analytics, and Big Data technologies. AWS Lambda streamlined tasks like nested JSON handling. NLP algorithms coupled with deep learning via Keras and TensorFlow enriched my skills, especially in information extraction. Designing and optimizing AWS-based data solutions was another forte, with AWS Cost Explorer optimizing resource allocation. Throughout data mining phases—collection, cleaning, model development, validation, visualization—I actively participated. Proficiency in predictive modeling, data mining methods, statistical techniques, and econometrics was foundational. Show less



Thomson Reuters

• Canada
• Software Development
• 700 & Above Employee

• Data Scientist

  • May 2013 - Jun 2016

  I gathered, analyzed, and documented application requirements, translating them into data models while promoting documentation standardization. My role included creating user-defined functions (UDFs) in Hive for data manipulation. Designing and developing machine learning frameworks using Python and Matlab was a focus. Data cleaning, feature scaling, and engineering were executed using pandas and NumPy in Python. I proficiently applied clustering algorithms like Hierarchical and K-means through Scikit and Scipy. Data migration to AWS S3 and building tables in AWS Athena using AWS Glue streamlined processes, enhancing efficiency. Collaborating with data engineers, I implemented ETL processes and optimized SQL queries for data extraction. Utilizing Recency, Frequency, and Monetary Value methodology was instrumental. SQL optimization transformed raw data into structured MySQL via Informatica, facilitating machine learning readiness. I managed end-to-end data pipelines through AWS services including S3, Glue, and EMR. My expertise spanned Spark, Scala, Hadoop, HQL, VQL, oozie, pySpark, Data Lake, TensorFlow, HBase, Cassandra, Redshift, MongoDB, Kafka, Kinesis, Spark Streaming, Edward, CUDA, MLLib, and a variety of machine learning methods. Tableau facilitated data visualization and interactive statistical analysis, aiding in presenting preliminary reports to stakeholders. I effectively implemented machine learning solutions within production environments, ensuring scalability. Testing models on AWS EC2 and collaborating with developers for optimal algorithms and parameters was pivotal. Data collection, cleaning, visualization, and feature engineering were seamlessly executed using Python libraries like Pandas, Numpy, Matplotlib, and Seaborn. I calculated revenue, applied K-means clustering for revenue score assignment, and implemented various methodologies. Show less