Machine Learning Data Science
Resume:
Padmelaxmi Viswanathan
**********@*****.***
https://www.linkedin.com/in/padmelaxmi
EDUCATION
Birla Institute of Technology and Science, Pilani, India
Oct 2020 – Sept 2022
Master of Technology in Data Science and Engineering
Relevant Coursework: Machine Learning Data Mining Artificial Intelligence Natural Language Processing Deep Learning Information Retrieval Graph Networking and Processing Big Data Systems Stream Processing and Analytics Data Visualization
Pondicherry Engineering College, Pondicherry, India
Jun 2004 – Apr 2008
Bachelor of Technology in Civil Engineering
Relevant Coursework: Mathematical Foundation Statistics C C# Java
PROFESSIONAL SUMMARY
Data Scientist with experience in executing data-driven solutions with adept knowledge on Data Analytics, Data Mining, Machine Learning (ML), Predictive Modeling, Natural Language Processing (NLP) and Graph Mining
Proficient in all aspects of a data science project life cycle including Data Extraction, Data Pre-Processing, Feature Engineering, Dimensionality Reduction, Statistical Modeling, Model Testing & Validation, Implementation and Data visualization
Spearheaded multiple high-profile Machine Learning projects and Agile projects collaborating with stakeholders across multiple business and tech teams, vendors and senior management
Proficient in Machine Learning techniques such as Linear and Logistics Regression, Decision Trees, Random Forest, SVM, Naive Bayes, K-Nearest Neighbors, Bayesian, Adaboost, XG Boost in Forecasting/ Predictive Analytics utilizing structured and unstructured data
Expert in building Computer Vision and Deep Learning applications
Expertise in Natural Language Processing (NLP) in python including tokenization, lemmatization, stemming, parts of speech tagging, sentimental analysis
Proficient in deep learning models like CNN, RNN, LSTM
Experience in using various python packages like Pandas, Keras, PyTorch, Tensorflow, Scikit-learn, OpenCV, NLTK, SciPy, NumPy, Matplotlib, Plotly, Seaborn
Experience in productionizing Machine Learning pipelines on Google cloud platform which performs data extraction, data cleaning, model training and updating the model on performance metrics
Achieved Continuous Integration and Continuous Deployment (CI/CD) for applications using Git, Subversion, Jenkins and Fast ARM
Expertise in creating data visualizations, dashboards and Ad-hoc reports in PowerBI, Tableau, Splunk, ELK and Microsoft Excel
Experience in building data warehouses, data marts for creating power BI reports to visualize various key performance indicators of business
Well versed in programming and debugging code written in languages including Python, Unix, COBOL, Mainframes
Ensured end-to-end on-time delivery adhering to/exceeding quality and security standards as a technical Lead
Equipped with technical and business acumen to arrive at design-related and data-driven decisions
Excellent leadership quality and managerial skills including experience in driving teams located in different geographic locations
Proficient in tracking and delivering multiple projects in parallel using Agile methodology
Strong skills in identifying process/performance improvements and automating repetitive processes by providing innovative value additions and cost saves
Experience in evaluating applications and platforms by conducting performance tests, identifying feasible alternative solutions and providing recommendations
As a Security Champion, proficient in assessing and ensuring application code and vendor software code is free from vulnerabilities and remediating
Strong in analytical ability, problem solving techniques, verbal and written communications, presentation and interpersonal skills
TECHNICAL SKILLS
Programming Languages
Python, SQL, Abinitio Programming, UNIX shell scripting, COBOL, REXX, Easytrieve, Powershell
Software Methodologies
Agile and Waterfall
Database Systems
Oracle, PostgreSQL, SQL Server, Snowflake, DB2, IMS
Operating Systems
Red Hat Enterprise Linux, z/OS, Windows
Cloud Technologies
AWS (EC2, S3), Microsoft Azure
Machine Learning Algorithms
Linear regression, Logistic regression, SVM, Decision tree, Random Forest, Boosting, Bagging, KNN, K-means clustering, Naïve bayes
Python packages
Pandas, Keras, PyTorch, Tensorflow, Scikit-learn, OpenCV, NLTK, SciPy, NumPy, Matplotlib, Plotly, Seaborn
Data Modeling Tools
Snowflake, Erwin Studio, Star-Schema, FACT and dimension tables, Pivot Tables
Reporting /Visualization
ELK, Splunk, Tableau, PowerBI, Crystal reports
ETL Tools
Ab Initio Suite of Products
Graphical Development Environment, Technical Repository Management Console, Enterprise Meta> Environment, Control Center, Abinitio Web EME, Conduct > It
HDFS, MapReduce, Spark, Storm, Kafka, Scala
Other Specialized Software/ Applications/ Tools
Open Text Exstream,
IDEs (Eclipse, PyCharm, Anaconda, Jupyter, Spyder, IntelliJ)
SQL clients (Squirrel, Toad, PGAdmin, DB2Visualizer, DBeaver),
Version Control (Jira, Git)
Release management (ServiceNow, HP Service Manager, ChangeMan)
Job Schedulers (Autosys, ControlM, Automic Scheduler)
EXPERIENCE
DATA SCIENTIST
Narvee Tech - CVS Heath
Chicago, IL Jul 2023 – Till Date
Responsibilities
Collaborated with business stakeholders and Subject Matter Experts to gather and discuss requirements.
Applied Machine Learning Algorithms such as Logistic Regression, Decision Tree, and Random Forest to implement predictive modeling got various types of business use cases.
Built a ML model to perform customer analysis and increase the sales by strategic email campaigning of offers to target customers.
Built monitoring dashboards that visualize the present and predicted values of customer centric features using Tableau.
Derive data from relational databases to perform complex data manipulations and conduct extensive data checks to ensure data quality.
Perform Data wrangling to clean, transform and reshape the data utilizing Numpy and Pandas library.
Productionized machine learning pipelines that gather data from BigQuery and build forecasting models to predict temperature and humidity spikes inside the warehouses
Work with datasets of varying degrees of size and complexity including both structured and unstructured data to perform Data mining, Data cleaning, Data collection, Variable selection, Feature engineering, Developing models, Validation, Visualization
DATA SCIENTIST
Singular Analysts Inc. - CVS Heath
Chennai, India Feb 2022 – Jun 2023
Responsibilities
Applied Machine Learning Algorithms such as Logistic Regression, Decision Tree, and Random Forest to implement predictive modeling got various types of business use cases.
Built a ML model to perform customer analysis and increase the sales by strategic email campaigning of offers to target customers.
Built monitoring dashboards that visualize the present and predicted values of customer centric features using Tableau.
Derive data from relational databases to perform complex data manipulations and conduct extensive data checks to ensure data quality.
Perform Data wrangling to clean, transform and reshape the data utilizing Numpy and Pandas library.
Productionized machine learning pipelines that gather data from BigQuery and build forecasting models to predict temperature and humidity spikes inside the warehouses
Work with datasets of varying degrees of size and complexity including both structured and unstructured data to perform Data mining, Data cleaning, Data collection, Variable selection, Feature engineering, Developing models, Validation, Visualization
PROGRAM LEAD
Datacaliper LLC – Capital One Munission Mi-Corporation Mutual Drug Dedrone
Chennai, India Jan 2021 – Jan 2022
Responsibilities
Led multiple machine learning and data analytics projects in parallel
oImage recognition and fingerprint matching to support Jail Management Systems and Record Management Systems
oGenerate caption and detailed description for road accidents using a picture to be stored in government records
oIdentify and exclude profanity from user messages that will be posted on Federal Government websites
oRecommendation engine using Market Basket Analysis and Inventory Restocking Analysis using time series forecasting for a pharmaceutical wholesaler with more than 23,000 products
Provided AI/ML consultation for a high-profile air space security project
Analyze and assess quality of data flow using Python and SQL
Retrieve, gather, organize, interpret and determine the meaning of data and metadata using data profiling techniques
Build dynamic mechanism to report business data quality to key stakeholders on real time
Create visualizations, reports and dashboards to provide insights and recommendations to business partners using Power BI, Splunk, ELK and Tableau
Collaborate with autonomous cross-functional teams, review development projects and test results
Accomplishments
Trained a team of 12 in Python, SQL and Power BI
Provided internal training sessions on Machine Learning, NLP and Graph Theory
Automated Ab Initio graph-to-file data lineage lookup process using shell script
Automated data profiling process using Python and SQL
LEAD DATA ANALYST
Datacaliper LLC – Capital One
Richmond, VA Oct 2018 – Dec 2020
Responsibilities
Meet with business stakeholders and Subject Matter Experts to gather and discuss requirements in pipeline
Analyze source database architecture and components to classify and categorize data elements to cater to growing business needs in target environment
Prepare new logical data model and create physical data model that suits the logical data model
Work with database administrators, business analysts to review and validate the models developed
Collect exhaustive metadata on business and technical front and complete data curation
Ensure data lineage is maintained across platforms by creating Business and Technical datasets in in-house metadata management tools
Analyze and assess quality of data that flows through the application and build dynamic mechanism to report business data quality to key stakeholders on real time
Drill down data to locate errors, share findings with upstream application and collaborate until root cause is fixed
Retrieve, gather, organize, interpret and determine the significance of data and metadata using data profiling techniques
Perform Oracle database validation using SQL Functions and Commands
Create rich visualizations, reports and dashboards to provide insights and recommendations to business partners using ELK and Splunk
Analyze Ab Initio code and help business understand legacy applications, develop solutions to modernize data applications and guide through data transformation from physical servers to cloud environment
Analyze code and arrive at end-to-end flow of data and establish data lineage
Collaborate with cross-functional teams, review development projects and test results, and ensure that data transformation and environment migration is completed without business impacts
Identifies and reports software defects and test findings using JIRA
Accomplishments
Identified a gap in business functionality and proposed optimization in Anti Money Laundering process
Automated Ab Initio graph-to-file data lineage lookup process using web scraping and shell script
Setup automated reporting to notify management about discrepancies in data quality on a regular basis
AB INITIO TECH LEAD
Tata Consultancy Services – JP Morgan Chase
Columbus, OH Feb 2013 – Oct 2018
Responsibilities
Build, maintain and upgrade Ab Initio environments using multiple versions of Ab Initio suite of products, OpenText, Streamdiff, CVision and Splunk hosted on RHEL servers and Windows servers
Participate in vendor software license and contract negotiations along with senior management, enable negotiations, install software licenses, and ensure that software license agreements are in compliance
Collaborate and lead the technical team in designing solutions for application functionalities, classifying and building data models for data elements.
Establish coding standards and best practices for the team to follow as part of application development
Create new or make changes to Ab Initio components as part of application development or maintenance projects
Review code changes/deliverables to make sure they adhere to standards and best practices
Work with QA team to identify test scenarios, number of cycles, testing schedule and reporting format
Review implementation documentation to make sure all standards and requirements are met before an application or code changes are deployed to production
Conduct performance tests after analyzing and observing existing Production volume and load peak, forecast trends and propose solutions to improve performance at application, infrastructure and Ab Initio configuration layers
Manage user setup and their accesses using KeON and EPV
Closely work with vendor support teams on issues and bugs with the softwares and roll out fixes
Collaborate with server support operations for work involving problem determination and implementation of changes to hardware, software, applications or network systems
Setup password-less connectivity between various servers in Linux, Windows and Mainframes platforms
As an Application Security Champion, identify and address security concerns in the application and infrastructure
Perform Disaster Recovery testing and prove sustained resiliency
Develop quick and easy Unix programs for ad-hoc reports, data extraction and for automating BAU activities
Take part in Agile ceremonies such as daily stand up, backlog grooming, review and retrospective meetings. Keep JIRA board updated with daily status of stories/tasks.
Set clear team goals and evaluate progress along the way and enable the team to work as a collaborative unit by resolving conflicts, if any.
Accomplishments
Completely owned and delivered Tech Refresh project that required building Ab Initio environment from scratch and involving 10 software and 23 versions, sftp connectivity with 58 interfacing applications on 11 application and web servers across multiple environments
Automated Ab Initio code migration to higher environments and code migration validation process using Unix Shell scripting which saves $180,000 per annum
Automated Black Duck Code scanning compliance process using Unix Shell Scripting saving $63,000 per annum
Automated change record creation process and transformed it from highly manual to a click of the button saving $96,000 per annum
Automated OpenText Exstream database administration activities using MS DOS scripts saving 1600 person hours per annum
DEVELOPMENT TEAM LEAD
Tata Consultancy Services – JP Morgan Chase
Chennai, India Nov 2011 – Feb 2013
Responsibilities
Gather requirements, draft high level and technical design and develop programs by following best practices, established coding standards and naming conventions for a platform migration project
Drive and co-ordinate test cycles in both IST and UAT environments to test all possible scenarios
Review code changes and test results to make sure they align to the requirements
Plan implementation activities, deploy code in Production environment, verify and validate code deployment after the implementation is complete
Provide post-implementation support and support future enhancements
Delegate and coordinate tasks with the team on all the above activities
Accomplishments
Performed Proof of Concept for migrating Document Composition application from COBOL (Mainframes) to Ab Initio hosted on Linux servers
Lead a team of 12 and migrated 80% of data processing (by volume) to target environment in less than two months
PRODUCTION SUPPORT ENGINEER
Tata Consultancy Services – JP Morgan Chase
Chennai, India Apr 2011 – Nov 2011
Responsibilities
Monitor Production batch cycle for multiple applications in parallel actively to make sure that they complete successfully and in compliance with Service Level Agreements (SLAs)
Triage, troubleshoot and mitigate problems with Linux, Mainframe and Windows based business applications
Acknowledge notification in case of job failures, determine cause of the issue, apply fixes as required and ensure SLA is met consistently
Identify root causes of technical issues in Production, and design and develop solutions to fix the identified issues
Ensure network, system and data availability and integrity through preventative maintenance on Linux servers
Engage subject matter experts from Development team or Operations team, as needed, in case of issues that occur due to a change introduced in the system
Interact with project teams for new releases and provide insight from technical issues of previous releases and Production batch cycle
Accomplishments
Created utility to generate customized reports from Service Manager tool to arrive at metrics and assess health of the application
Streamlined Production support process and protocols which greatly reduced response and resolution time
MAINFRAMES DEVELOPER
Tata Consultancy Services – JP Morgan Chase
Chennai, India Sep 2008 – Apr 2011
Responsibilities
Draft technical design after thoroughly understanding requirements and develop programs following best practices, established coding standards and naming conventions for a bank merger project
Test code thoroughly in both IST and UAT environments with all possible test cases and through regression testing, stress testing, positive/negative testing and boundary condition testing
Ensure code readiness for Production deployment, verify and validate code deployment after the implementation is complete and perform production simulation testing
Provide post-implementation support and support future enhancements
Document test results, observations, best practices and lessons learnt during the course of the project
Accomplishments
Developed a tool to validate correctness of Zeke scheduler events across development and QA regions
**********@*****.***
https://www.linkedin.com/in/padmelaxmi
Contact this candidate