SUMMARY

• 9+ years of experience in Machine Learning,Datamining, Data Architecture, Data Modeling, Data Mining, Data Analysis, NLP with largedatasets of Structured and Unstructureddata,DataAcquisition,DataValidation, Predictive modeling,DataVisualization, Web Crawling, Web Scraping, Adept in statistical programming languages like R and Python including BigDatatechnologies like Hadoop, Hive, HDFS, MapReduce and NoSQL Based Databases.
• Proficient in managing entire data science project life cycle and actively involved in all the phases of project life cycle including data acquisition, data cleaning, data engineering, features scaling, features engineering, statistical modeling (decision trees, regression models, neural networks, SVM, clustering), dimensionality reduction using Principal Component Analysis and Factor Analysis, testing and validation using ROC plot, K - fold cross validation and data visualization.
• Very good experience and knowledge in provisioning virtual clusters under AWS cloud which includes services like EC2, S3, and EMR.
• Adept and deep understanding of Statistical modeling, Multivariate Analysis, model testing, problem analysis, model comparison and validation.
• Excellent knowledge of Machine Learning, Mathematical Modeling and Operations Research. Comfortable with R, Python, SAS and Weka, MATLAB, Relational databases. Deep understanding & exposure of BigDataEco-system.
• Expertise in transforming business requirements into analytical models, designing algorithms, building models, developingdatamining and reporting solutions that scales across massive volume of structured and unstructureddata.
• Experienced inDataModeling techniques employingDatawarehousing concepts like star/snowflake schema and Extended Star.
• Excellent working experience and knowledge in Hadoop eco-system like HDFS, MapReduce, Hive, Pig, MongoDB, Cassandra, HBase.
• Expert in creating PL/SQL Schema objects like Packages, Procedures, Functions, Subprograms, Triggers, Views, Materialized Views, Indexes, Constraints, Sequences, Exception Handling, Dynamic SQL/Cursors, Native Compilation, Collection Types, Record Type, Object Type using SQL Developer.
• Excellent knowledge and experience in OLTP/OLAP System Study with focus on Oracle Hyperion Suite of technology, developing Database Schemas like Star schema and Snowflake schema (Fact Tables, Dimension Tables) used in relational, dimensional and multidimensional modeling, physical and logical Data modeling using Erwin tool.
• Expertise in performingdataparsing,datamanipulation anddatapreparation with methods including describedatacontents, compute descriptive statistics ofdata, regex, split and combine, Remap, merge, subset, reindex, melt and reshape.
• Experienced indatamining & loading and analyzing unstructureddata-XML, JSON, flat file formats into Hadoop.
• Experienced in using various packages in Rand python like ggplot2, caret, dplyr, Rweka, gmodels, RCurl, tm, C50, twitteR, NLP, Reshape2, rjson, plyr, pandas, numpy, seaborn, scipy, matplotlib, scikit-learn, Beautiful Soup, Rpy2.
• Extensive experience in Text Analytics, generatingdatavisualizations using R, Python and creating dashboards using tools like Tableau.
• Excellent hands on experience with bigdatatools like Hadoop, Spark, Hive, Pig, Impala, Pyspark, SparkSql.
• Experienced in Teradata RDBMS using Fast load, Fast Export, Multi load, T pump, and Teradata SQL Assistance and BTEQ Teradata utilities.
• Expertise in Excel Macros, Pivot Tables, vlookups and other advanced functions and experience with working in Agile/SCRUM software environments.
• Hands on experience in implementing LDA, Naive Bayes and skilled in Random Forests, Decision Trees, Linear and Logistic Regression, SVM, Clustering, neural networks, Principle Component Analysis.
• Extensive experience inDataVisualization including producing tables, graphs, listings using various procedures and tools such as Tableau.

TECHNICAL SKILLS

Data Analytics Tools/Programming: Python (numpy, scipy, pandas,Gensim, Keras), R ( Caret, Weka, ggplot), MATLAB, Microsoft SQL Server, Oracle PLSQL, Python.

Data Visualization: Tableau, Visualization packages, Microsoft Excel.

Machine Learning Algorithms: Classifications, Regression, Clustering, Feature Engineering.

Data Modeling: Erwin 9.x, Star Schema, Snow-Flake Schema, ER Studio.

Big Data Tools: Hadoop, MapReduce, SQOOP, Pig, Hive, NOSQL, Cassandra, MongoDB, Spark, Scala.

Databases: Oracle, SQL Server, Teradata, Netezza, DB2.

ETL: Informatica, SSIS.

Others: Deep Learning, Graph Mining, Text Mining, C, C++, Java, Javascript, ASP, Shell Scripting, Scala npl, Spark MLLib, SAS, SPSS, Cognos.

PROFESSIONAL EXPERIENCE

Confidential, Basking Ridge NJ

Sr. Data Scientist/Data Architect

Responsibilities:

• Developed analytics solutions based on Machine Learning platform and demonstrated creative problem-solving approach and strong analytical skills.
• Interacted with the other departments to understand and identifydataneeds and requirements and work with other members of the IT organization to Qlikview based deliverdatavisualization and reporting solutions to address those needs
• Worked with Architecture team to get the metadata approved for the new data elements that are added for this project.
• DataStory teller, MiningDatafrom differentDataSource such as SQL Server, Oracle, Cube Database, Web Analytics, Business Object and Hadoop. Provided AD hoc analysis and reports to executive level management team.
• Creating various B2B Predictive and descriptive analytics using R and Tableau
• Exploratory analysis and model building to develop predictive insights and visualize, interpret, report findings and develop strategic uses ofdata.
• Utilized Spark, Scala, Hadoop, HBase, Kafka, Spark Streaming, MLLib, R, a broad variety of machine learning methods including classifications, regressions, dimensionally reduction etc.
• Designed and provisioned the platform architecture to execute Hadoop and machine learning use cases under Cloud infrastructure, AWS, EMR, and S3.
• Selection of statistical algorithms - (Two Class Logistic Regression Boosted Decision Tree, Decision Forest Classifiers etc)
• Used MLlib, Spark's Machine learning library to build and evaluate different models.
• Worked in using Teradata14 tools like Fast Load, Multi Load, T Pump, Fast Export, Teradata Parallel Transporter (TPT) and BTEQ.
• Involved in creatingDataLake by extracting customer's BigDatafrom variousdatasources into Hadoop HDFS. This includeddatafrom Excel, Flat Files, Oracle, SQL Server, MongoDb, Cassandra, HBase, Teradata, Netezza and also logdatafrom servers
• Used Spark Data frames, Spark-SQL, SparkMLLibextensively and developing and designing POC's using Scala, Spark SQL andMLliblibraries.
• Created high level ETL design document and assisted ETL developers in the detail design and development of ETL maps using Informatica.
• Used R, SQL to create Statistical algorithms involving Multivariate Regression, Linear Regression, Logistic Regression, PCA, Random forest models, Decision trees, Support Vector Machine for estimating the risks of welfare dependency.
• Helped in migration and conversion of data from the Sybase database into Oracle database, preparing mapping documents and developing partial SQL scripts as required.
• Generated ad-hoc SQL queries using joins, database connections and transformation rules to fetch data from legacy Oracle and SQL Server database systems
• Executed ad-hocdataanalysis for customer insights using SQL using Amazon AWS Hadoop Cluster.
• Worked on predictive and what-if analysis using R from HDFS and successfully loaded files to HDFS from Teradata, and loaded from HDFS to HIVE.
• Designed the schema, configured and deployed AWSRedshiftfor optimal storage and fast retrieval ofdata.
• Analyzed data and predicted end customer behaviors and product performance by applying machine learning algorithms using SparkMLlib.
• Performed data mining on data using very complex SQL queries and discovered pattern and Used extensive SQL fordataprofiling/analysis to provide guidance in building thedatamodel
• Used the Agile Scrum methodology to build the different phases of Software development life cycle.
• Designed and implemented system architecture for Amazon EC2 based cloud-hosted solution for client.
• NLTK, StanfordNLP, RAKE to preprocess the data, entity extraction and keyword extraction.
• Create Control-M and Oozie workflow scripts to automate theDataingestion process into HadoopDataLake.
• Used External Loaders like Multi Load, T Pump and Fast Load to loaddatainto Teradata Database, Involved in analysis, development, testing, implementation and deployment.
• Created numerous dashboards in tableau desktop based on thedatacollected from zonal and compass, while blendingdatafrom MS-excel and CSV files, with MS SQL server databases.

Environment: R, Machine Learning, Teradata 14, Hadoop Map Reduce, Pyspark, Spark, R, Spark MLLib, Tableau, Informatica, SQL, Excel, VBA, BO, CSV, Erwin, SAS, AWS Redshift, Scala Nlp, Cassandra, Oracle, MongoDB, Informatica MDM, Cognos,SQL Server 2012, Teradata, DB2, SPSS, T-SQL, PL/SQL, Flat Files, XML, and Tableau

Confidential, Brooklyn NY

Sr. Data Scientist/Data Architect

Responsibilities:

• Application of various machine learning algorithms and statistical modeling like decision trees, regression models, neural networks, SVM, clustering to identify Volume using scikit-learn package in python, Matlab
• Utilized Apache Spark with Python to develop and execute Big Data Analytics and Machine learning applications, executed machine Learning use cases under Spark ML and Mllib.
• Led technical implementation of advanced analytics projects, Defined the mathematical approaches, developer new and effective analytics algorithms and wrote the key pieces of mission-critical source code implementing advanced machine learning algorithms utilizing caffe, TensorFlow, Scala, Spark, MLLib, R and other tools and languages needed.
• Built analytical data pipelines to port data in and out of Hadoop/HDFS from structured and unstructured sources and designed and implemented system architecture for Amazon EC2 based cloud-hosted solution for client.
• Performed K-means clustering, Multivariate analysis and Support Vector Machines in Python and R.
• Professional Tableau user (Desktop, Online, and Server), Experience with Keras and Tensor Flow.
• Involved in creatingDataLakeby extracting customer's BigDatafrom variousdatasources into Hadoop HDFS. This includeddatafrom Excel, Flat Files, Oracle, SQL Server, MongoDb, Cassandra, HBase, Teradata, Netezza and also logdatafrom servers
• Created mapreduce running over HDFS for data mining and analysis using R and Loading & Storage data to Pig Script and R for MapReduce operations and created various types of data visualizations using R, and Tableau.
• Worked on machine learning on large sizedatausing Spark and MapReduce.
• Performeddataanalysis by using Hive to retrieve thedatafrom Hadoop cluster, SQL to retrievedata from Oracle database.
• DevelopedSpark/Scala, Python for regular expression (regex) project in the Hadoop/Hive environment with Linux/Windows for bigdataresources.
• Performed Multinomial Logistic Regression, Random forest, Decision Tree, SVM to classify package is going to deliver on time for the new route.
• Stored and retrieveddatafromdata-warehouses using AmazonRedshift.
• Responsible for planning & scheduling new product releases and promotional offers.
• Used pandas, numpy, seaborn, scipy, matplotlib, scikit-learn, NLTK in Python for developing various machine learning algorithms.
• Worked on NOSQL databases like MongoDB, HBase.
• CreatedDataQuality Scripts using SQL and Hive to validate successfuldataload and quality of thedata. Created various types ofdatavisualizations using Python and Tableau.
• Worked ondatapre-processing and cleaning thedatato perform feature engineering and performeddataimputation techniques for the missing values in the dataset using Python.
• Extracteddatafrom HDFS and prepareddatafor exploratory analysis usingdatamunging.
• Worked on Text Analytics, Naive Bayes, Sentiment analysis, creating word clouds and retrievingdatafrom Twitter and other social networking platforms.
• Worked on differentdataformats such as JSON, XML and performed machine learning algorithms in Python.

Environment: Python, MongoDB, JavaScript, SQL Server, HDFS, Pig, Hive, Oracle, DB2, Tableau, ETL (Informatica), SQL, T-SQL, EC2, EMR, Teradata, Hadoop Framework, AWS, Spark SQL, Scala, SparkMllib, NLP, SQL, Matlab, HBase, Cassandra, R, Pyspark, Tableau Desktop, Excel, Linux, CDH5, Informatica MDM.

Confidential, Dallas TX

Sr. Data Modeler/Data Architect

Responsibilities:

• Involved in data management including Data Modeling, Metadata, Data Analysis, Data mapping and Data Dictionaries, Erwin9.1 and involved in Data Modeling (Oracle/MySQL/Netezza), Data Characterization, Workflow design and implementation
• Used ErwinDataModelerand Erwin Model Manager to create Conceptual, Logical and Physical data models and maintain the model versions in Model Manager for further enhancements.
• Worked on logical and physical modeling of various data marts as well as data warehouse using Taradata14.
• Created and maintained LogicalDataModel (LDM) for the project. Includes documentation of all entities, attributes,datarelationships, primary and foreign key structures, allowed values, codes and glossary terms in accordance with the CorporateDataDictionary etc.
• Implemented Bulk Load Process by converting existing Triggers toOracle11g packages to improve the Data loading process.
• Designed and Developed Oracle11g, PL/SQL Procedures and UNIX Shell Scripts forData Import/Export andDataConversions.
• Maintained warehouse metadata, naming standards and warehouse standards.
• Involved in the validation of the OLAP Unit testing and System Testing of the OLAP Report Functionality anddatadisplayed in the reports.
• Worked in using Teradata14.1 tools like Fast Load, Multi Load, T Pump, Fast Export, Teradata Parallel Transporter (TPT) and BTEQ.
• Designed the overall ETL solution including analyzing data, preparation of high level, detailed design documents, test plans and deployment strategy.
• Strong knowledge of Entity-Relationship concept, Facts and dimensions tables, slowly changing dimensions and Dimensional Modeling (Star Schema and Snow Flake Schema).
• Created Software Development Life Cycle (SDLC) document and excelled in the process of Change Management, Release management and Configuration processes.
• PreparedDataVisualization reports for the management using R
• Documented logical, physical, relational and dimensionaldatamodels. Designed theDataMarts in dimensionaldatamodeling using star and snowflake schemas.
• Involved inNormalizationandDe-Normalizationof existing tables for faster query retrieval.
• CreateMDMbase objects, Landing and Staging tables to follow the comprehensive data model in MDM.
• Used ETL methodology for supportingdataextraction, transformations and loading processing, in a complex MDM using Informatica.
• PerformedDataValidation andDataCleaning using PROC SORT, PROC FREQ and through various SAS formats.
• DesignedDataStaging Area andDataWarehouse to integrate thedatafrom various sources including Flat Files to facilitate management to make more fact based decisions.
• Created jobs, alerts to run SSIS,SSRSpackages periodically. Created the automated processes for the activities such as database backup processes and SSIS,SSRSPackages run sequentially using SQL Server Agent job and windows Scheduler.
• Manageddatain different locations using differentdatamarts usingAzure.
• Perform reverse engineering of physicaldatamodels from databases and SQL scripts.
• Involved in Normalization (3rd normal form), De-normalization (Star Schema forDataWarehousing.
• Used SSIS to create ETL packages to validate, extract, transform and load data to data warehouse databases, data mart databases to OLAP databases.
• Implemented slowly changing dimensions Type2 and Type3 for accessing history of referencedata changes.
• Extensively used SAS to query and subset data, summarize and present data, combine tables using joins and merges and created and modified tables.
• Combined views and reports into interactive dashboards inTableauDesktop that were presented to Business Users, Program Managers, and End Users.
• Utilized SDLC and Agile methodologies such as SCRUM.
• Worked in PL/SQL Programming (Stored procedures, Triggers, Packages) using Oracle (SQL, PL/SQL), SQL Server2008 and UNIX shell scripting to perform job scheduling.

Environment: ERwin9.1, Teradata14, Oracle10g, PL/SQL, UNIX, Agile, Azure, TIDAL, MDM, ETL, BTEQ, SQL Server2008, Informatica MDM, Netezza, DB2, SAS, Tableau, UNIX, SSRS, SSIS, T-SQL, MDM, Informatica, SQL

Confidential, Chantilly, VA

Sr. Data Modeler/Data Analyst

Responsibilities:

• Created physical and logical models and used Erwin9.1 for DimensionalDataModeling.
• Designed and Developed Oracle PL/SQL Procedures and UNIX Shell Scripts forDataImport/Export anddataConversions.
• Performed legacy applicationdatacleansing,dataanomaly resolution and developed cleansing rule sets for ongoing cleansing anddatasynchronization.
• Extensively used Star Schema methodologies in building and designing the logicaldatamodel into Dimensional Models.
• Involved in project cycle plan for thedatawarehouse, sourcedataanalysis,dataextraction process, transformation and loading strategy designing.
• Worked on Conceptual, Logical Modeling and Physical Database design for OLTP and OLAP systems.
• Designed a STAR schema for salesdatainvolving shared dimensions (Conformed) using Erwin DataModeler.
• Designed and build the OLAP cubes using Star schema and Snow Flake Schema using native OLAP Service Manager.
• Extensively used Teradata utilities (BTEQ, Fast load, Multiload, TPUMP) to import/export and load thedatafrom oracle, flat files.
• PerformedDataAnalysis tasks on warehouses from several sources like Oracle, DB2, and XML etc and generated various reports and documen6ts.
• Created Database Maintenance Plans for the performance of SQL Server which covers Database Integrity checks, update database Statistics and Re-indexing.
• Involved in workflows and monitored jobs using Informatica tools. Developed SQL, PL/SQL and ETL scripts on UNIX.
• Migrated data from SAS environment to SQL Server 2008 via SQL Integration Services (SSIS)
• Used External Loaders like Multi Load, T Pump and Fast Load to loaddatainto Teradata Database, Involved in analysis, development, testing, implementation and deployment.
• Used SSIS to create ETL packages to Validate, Extract, Transform and LoaddataintoData Warehouse andDataMart.
• Merging SAS datasets, Macro facility, SAS Graphs, SAS Formats, SAS Functions, storing and managingdatain SAS files
• Developed stored procedures on Netezza and SQL server fordatamanipulation anddata warehouse population
• Actively involved in Normalization (3NF) & De-normalization of database.
• Involved in implementing of SQL Server 2008.
• Developed multiple processes for Daily Data Ingestion from Client associated data vendors and Production Team, Client site employees using SSIS andSSRS
• Setting up Connection Strings and connecting SQL ServerAZUREDatabases from locally Installed SQL Server Management Studio (SSMS) for Developers
• Created multiple custom SQL queries in Teradata SQL Workbench to prepare the right data sets forTableaudashboards. Queries involved retrieving data from multiple tables using various join conditions that enabled to utilize efficiently optimized data extracts forTableauworkbooks.
• Resolved thedatatype inconsistencies between the source systems and the target system using the mapping documents and analyzing the database using SQL queries.
• Extensively used Extract Transform Loading (ETL) tool of SQL Server to populate data from various data sources
• Extensively used SQL Loader to loaddatafrom the Legacy systems into Oracle databases using control files and used Oracle External Tables feature to read thedatafrom flat files into Oracle staging tables.

Environment: - ERwin9.1,DataModeling, Informatica Power Center9.6, Taradata SQL, PL/SQL, BTEQ, DB2, Oracle, Agile, ETL, Tableau, Cognos, MDM, Business Objects, UNIX, SQL Server2008, Azure, TOAD, SAS, SSRS, SSIS, T-SQL etc.

Confidential

DataAnalyst/Data Modeler

Responsibilities:

• Data analysis and reporting using MY SQL, MS Power Point, MS Access and SQL assistant.
• Involved in MY SQL, MS Power Point, MS Access Database design and design new database onNetezzawhich will have optimized outcome.
• Used DB2 Adapters to integrate betweenOracledatabase and Microsoft SQL database in order to transfer data
• Designed thedatamarts using the Ralph Kimball's DimensionalDataMart modeling methodology using ER Studio.
• Involved in writing T-SQL, working on SSIS, SSRS, SSAS, Data Cleansing, Data Scrubbing and Data Migration.
• UsedNormalizationmethods up to 3NF andDe-normalizationtechniques for effective performance in OLTP systems.
• Initiated and conducted JAD sessions inviting various teams to finalize the requireddatafields and their formats.
• Involved in designing and implementing thedataextraction (XMLDATAstream) procedures.
• Created base tables, views, and index. Built a complex Oracle procedure in PL/SQL for extract, loading, transforming thedatainto the warehouse via DBMS Scheduler from the internaldata.
• Involved in writing scripts for loadingdatato targetdataWarehouseusing Bteq, Fast Load, MultiLoad
• Create ETL scripts using Regular Expressions and custom tools (Informatica, Pentaho, and Sync Sort) to ETL data.
• Developed SQL Service Broker to flow and sync of data from MS-I to Microsoft's master database management (MDM).
• Extensively involved in Recovery process for capturing the incremental changes in the source systems for updating in the staging area anddatawarehouserespectively
• Strong knowledge of Entity-Relationship concept, Facts and dimensions tables, slowly changing dimensions and Dimensional Modeling (StarSchemaandSnowFlakeSchema).
• Involved in loading data betweenNetezzatables using NZSQL utility.
• Worked onDatamodeling using DimensionalDataModeling, Star Schema/Snow Flake schema, and Fact & Dimensional, Physical & Logicaldatamodeling.
• Generated Stats pack/AWR reports fromOracledatabase and analyzed the reports for Oracle8.xwait events, time consuming SQL queries, table space growth, and database growth.

Environment: ER Studio, MY SQL, MS Power Point, MS Access, MY SQL, MS Power Point, MS Access, Netezza, DB2, T-SQL, DTS, Informatica MDM, SSIS, SSRS, SSAS, ETL, MDM, 3NF andDe-normalization, Teradata, Oracle8.x, (StarSchemaandSnowFlakeSchema) etc.