SUMMARY

• An IT professional with Around 10+ years of experience as a Data Scientist and Business Intelligence Consultant using Machine Learning, Statistical Modeling, Data Mining, Natural Language Processing and Data Visualization and using R, Python, Spark, Scala, Hive, Hadoop, SAP Business Objects, Xcelsius 2008, Crystal Reports, Micro Strategy, Tableau, Oracle and Informatica Power Center within several business areas including Engineering, Pharma, Sales/Marketing, Medical, Healthcare, Learning & Development, Aviation and Federal.
• Experience as a Data Scientist architecting and building Data Science solutions using Machine Learning, Statistical Modeling, Data Mining, Natural Language Processing(NLP) and Data Visualization
• Experience working with large data source (5Bn rows+); interpret and communicate insights and finding from analysis and experiment to both technical and non - technical audience in products, service and business
• Domain expertise in architecting and building comprehensive analytical solutions in Marketing, Sales and Operations functions across Technology, Manufacturing, Retail and Pharmaceutical industries
• Good experience of contributing to successful end to end analytic solutions (clarifying business objectives and hypotheses, communicating project deliverables and timelines and informing action based on findings)
• Proactive participation in products roadmap discussions, data science initiatives and teh optimal approach to apply teh underlying algorithms
• Hands on experience building regression, classification and recommender systems with large datasets in distributed systems and a constrained environment
• Expert knowledge in breath of machine learning algorithms and love to find teh best approach to a specific problem. Implemented several supervised and unsupervised learning algorithms such as Ensemble methods (Random forests), Logistic Regressions, Regularized Linear Regression, Deep Neural Networks, Extreme Gradient Boosting, Decision Trees, Hierarchical models, and time series models (ARIMA, GARCH, VARCH etc.)
• Experience in Data Modeling retaining concepts of RDBMS, Logical and Physical Data Modeling until 3NormalForm(3NF) and Multidimensional Data Modeling Schema (Star schema, Snow-Flake Modeling, Facts and dimensions)
• Well versed writing production ready code in R, Python and SQL
• Developed and deployed dashboards in Xcelsius/Tableau to identify trends and opportunities, surface actionable insights and halp teams set goals. Forecast and prioritization of initiatives
• Experience in Data Analysis, Data Migrations, Data Cleaning, Transformation, Integration, Data Imports and Data Exports
• Hands on experience in optimizing teh SQL Queries and database performance tuning in Oracle and SQL Server database
• Strong expertise in using Tableau software as applied to BI data analytics, reporting and dashboard projects
• Expertise in teh Big Data ecosystem - Spark, Scala, Hive, Data Lake, Hadoop, HDFS, Scoop
• Good Knowledge in Data warehousing concepts
• Expertise in working with relational databases such as oracle 11g/12c and SQL Server
• Extensive experience in developing Stored Procedures, Functions, Views, Triggers and Complex SQL queries using Oracle PL/SQL
• Good experience in creating reports using SAP Crystal Reports 2008
• Expertise in debugging and optimizing teh Business Objects universes, WEBI Reports, Xcelsius Dashboards and Informatica mappings / workflows
• Implemented projects in various project methodologies - ASAP, Agile and Waterfall

TECHNICAL SKILLS

Languages: Python, R and SQL.

Database: Oracle MS SQL and SQL Server.

Hadoop: HDFS, MapReduce, Pig, Hive.

Libraries: Scikit-learns, Keras, TensorFlow, Numpy, Pandas, NLTK, Gensim, Matplotib, ggplot2.

Operating Systems: Linux, MAC OS, Windows.

ETL/Reporting: Business Objects (BI 4.1, BI 4.0, XI R3.1 and XI R2) Web Intelligence, Rich Client, Universe Design Tool (UDT), Information Design Tool (IDT), Universe Designer, Live Office, QaaWS, SAP BO Design Studio, SAP BO Dashboards (Xcelsius 2008), Crystal Reports 2008, Tableau, MicroStrategy and Informatica Power Center 7.1.9/9.1.6.

Methodologies: Agile, Scrum, Waterfall.

PROFESSIONAL EXPERIENCE

Confidential, Washington DC

Senior Data Scientist

Responsibilities:

• Expertise in applying teh data mining, machine learning, natural language processing, time series modelling in teh service domain.
• Sound understanding of service business and implementation of Machine Learning algorithms, Data modeling techniques in teh service domain.
• Hands on experience in Natural Language processing, sentiment analysis, Symantec Analysis and Topic extraction, Machine Learning algorithms, Ordinal regression, time series forecasting techniques, SMOTE- Synthetic Minority Over Sampling Techniques to handing teh imbalanced datasets.
• Delivered a predictive model using random forest classification model to predict possibility of denial of service attack. Significant improvement on prediction was achieved by using grid search technique.
• Worked on exploratory data analysis, data cleaning, visualization, Statistical Modeling using Python 3.5, R Studio, R Shiny and Tableau.
• Highly conversant in using teh machine learning models such as Linear, Logistics and Penalized Linear regression, Decision Trees, Random Forest, Support Vector Machines, Stochastic Gradient Boosting, K Mean, K nearest, Xgboost.
• Solid exposure in querying teh relational database like SQL Server and Oracle.
• Extensively used open source tools- R Studio, Python for statistical analysis and building teh machine learning.
• Experience in using advance data analysis models, Linear and teh constraint optimization models for a multiple brand.
• Solid understanding of working on Artificial Neural Nets and Deep Learning models using Theano and Tensor flow packages using in Python.

Environment: R Studio, R Shiny, Python 3.5, Tableau, SQL Server, Oracle

Confidential, Harford, CT

Data Analyst/ Scientist

Responsibilities:

• Designing and developing various machine learning frameworks using python and R.
• Built a metrics gathering, storing and reporting framework for teh Management team to consume and make data driven decision to plan teh workload on teh developers of different teams.
• Performeddataintegrity checks,data cleaning, exploratory analysis and feature engineer using R 3.4.0.
• Conducted analysis on assessing customer consuming behaviors and discover value of customers with RMF analysis; applied customer segmentation with clustering algorithms such as K-Means Clustering and Hierarchical Clustering.
• Developed personalized products recommendation with Machine Learning algorithms, including Collaborative filtering and Gradient Boosting Tree, to better meet teh needs of existing customers and acquire new customers.
• Worked on outliers’ identification with box-plot, K-means clustering using Pandas, Numpy.
• Participated in features engineering such as feature intersection generating, feature normalize and Label encoding with Scikit-learn preprocessing.
• Used Python 3.0 (numpy, scipy, pandas, scikit-learn, seaborn, NLTK) to develop variety of models and algorithms for analytic purposes.
• Coordinated teh execution of A/B tests to measure teh TEMPeffectiveness of personalized recommendation system.
• Performeddatavisualization with Tableau 10 and generated dashboards to present teh findings.
• Determined customer satisfaction and halped enhance customer experience using NLP.
• Used Git 2.6 to apply version control. Tracked changes in files and coordinated work on teh files among multiple team members.

Environment: R3.4.0, R Studio, Python 3.0, Tableau 10, SQL Server and Oracle

Confidential, Bayport, MN

SAP BO/Crystal Reports Developer

Responsibilities:

• Collaborate TEMPeffectively with operations Managers and Business Analysts to gather requirements.
• Design, Develop and test Crystal Reports based on detailed specifications.
• Creating project related documents and testing documents, release notes, Change request forms as per industry standards.
• Develop and test PL/SQL code for developed crystal reports using Oracle PL/SQL Developer
• Propose and design optimized solution for complex reports using analytical and specialized technical skills.
• Modifying existing complex reports based on functional changes.
• Create parameterized crystal reports using tables, queries and verify joins between them
• Created crystal reports for Details, Summary, Cross-tab reports using filters, Sorting, Groupings based on different fields.
• Format reports in Crystal Design before moving to Production.
• Participate and contribute in daily SCRUM meetings to achieve organizational goal as team and as an individual.

Environment: SAP Business Objects 4.X, Crystal Reports 2008 and Oracle

Confidential, Dallas, TX

SAP Business Objects / Xcelsius Developer

Responsibilities:

• Analyzing teh Client Requirements and preparing teh Dashboard specification document.
• Worked on modification of Universes.
• Developed WebI reports using various functions, operators, report filters and variables.
• Developed teh WebI reports and created live office objects to these reports.
• Worked on Conceptual design of teh Dashboard.
• Involved in Data Connectivity to teh databases using Query as a Web Service (QaaWS) connections.
• Worked on teh Performance tuning of teh Dashboard.
• Worked on Designing teh Dashboard according to Color style guide given by client.
• Conducted Unit Testing of teh Dashboard.
• Worked on Change Requests of teh existing Dashboards.

Environment: SAP Business Objects 4.X, Xcelsius 2008 and Oracle

Confidential, Schaumburg, IL

SAP Business Objects Developer

Responsibilities:

• Analyzed theexisting Business landscape, scope of work and gatheird teh reporting required specifications and documents
• Prepared Gap Analysis document based on teh exisiting documents
• Conversion of teh existing Crystal reports into Web I reports
• Automating teh existing manually running WebI and Crystal reports into WebI reports
• Designing teh Bobj Unverse in IDTusig MS SQL Server dataand developing teh Webi reports.
• Analyzing and updating teh exisiting BEX queries. Creating WebI repoton top of theBEx queries
• Extensively worked on analyzing data by running BEx queries using BEx analyzer
• Comparing data from source system SAP ECC and validarting teh data in BW Cubes and WebI reports
• Validating teh data writing custom SQL using SQL server management studio. Performing teh System testing and migrating Universe and reports to QA
• Prepared detailed technical documentation of teh Webi report design

Environment: SAP Business Objects 4.X and Oracle

Confidential, Burbank, CA

Informatica ETL Developer

Responsibilities:

• Gatheird business requirements from Business user.
• Designed and implemented appropriate ETL mappings to extract and transform data from various sources.
• Designed and developed Informatica ETL mappings to extract master and transactional data from multiple source systems.
• Installed and Configured teh Informatica Client tools.
• Worked on loading of data from several flat files to XML Targets.
• Designed teh procedures for getting teh data from all systems to Data Warehousing system.
• Created teh environment for Staging area, loading teh Staging area with data from multiple sources.
• Analyzed business process workflows and assisted in teh development of ETL procedures for moving data from source to target systems.
• Used workflow manager for session management, database connection management and scheduling of jobs.
• Monitored sessions using teh workflow monitor, which were scheduled, running, completed or failed. Debugged mappings for failed sessions.

Environment: Informatica Powercenter9.1.6 and Oracle

Confidential

PL/SQL and Informatica ETL Developer

Responsibilities:

• Analyzed teh business requirements and functional specifications.
• Extracted data from oracle database and spreadsheets and staged into a single place and applied business logic to load them in teh central oracle database.
• Used Informatica Power Center 8.6 for extraction, transformation and load (ETL) of data in teh data warehouse.
• Extensively used Transformations like Router, Aggregator, Normalizer, Joiner, Expression and Lookup, Update strategy and Sequence generator and Stored Procedure.
• Developed complex mappings in Informatica to load teh data from various sources.
• Implemented performance tuning logic on targets, sources, mappings, sessions to provide maximum efficiency and performance.
• Parameterized teh mappings and increased teh re-usability.
• Used Informatica Power Center Workflow manager to create sessions, workflows and batches to run with teh logic embedded in teh mappings.
• Created procedures to truncate data in teh target before teh session run.
• Extensively used Toad utility for executing SQL scripts and worked on SQL for enhancing teh performance of teh conversion mapping.
• Used teh PL/SQL procedures for Informatica mappings for truncating teh data in target tables at run time.
• Extensively used Informatica debugger to figure out teh problems in mapping. Also involved in troubleshooting existing ETL bugs.
• Created a list of teh inconsistencies in teh data load on teh client side so as to review and correct teh issues on their side.
• Created teh ETL exception reports and validation reports after teh data is loaded into teh warehouse database.
• Written documentation to describe program development, logic, coding, testing, changes and corrections.
• Created Test cases for teh mappings developed and tan created integration Testing Document.
• Followed Informatica recommendations, methodologies and best practices.

Environment: Informatica Powercenter9.1.6 and Oracle