PROFESSIONAL SUMMARY

• Six years of experience as a Data Scientist/Modeler with experience in analyzing, cleaning, wrangling, coding, implementing, testing, and maintaining database solutions using Statistical solutions.
• Experienced in engaging R Programming, MATLAB, SAS, Python, Tableau and SQL fordata cleaning,Statistical Modelling, datavisualization, risk analysis and predictive analysis
• Experience in creating data visualizations using Tableau software
• Publishing and presenting dashboards, Creating Storyline on web and desktop platforms.
• Worked on End to End Data Mining and Machine Learning Project Life Cycle.
• Worked on Statistical / Machine Learning Model building and Validation using Decision Tree, Linear & Logistic Regression, Support Vector Machine algorithms.
• Expertise in dealing with large datasets with R, Python and math libraries like Pandas, Numpy, Scipy
• Knowledge of Big Data technologies like MapReduce, Hadoop, Spark, etc.
• Worked and extracted data from various database sources like Oracle, SQL Server, DB2, and Teradata.
• Self - Motivated with Excellent communication skills with a strong focus on Client oriented service and ability to work excellently as an individual and as part of a team with minimum amount of supervision.
• Assist in evaluating and recommending analytical solutions based on digital trends/ transformations, market places, and economics of Banking, Financial Services, Telecom, Retail, and Utility industries.

TECHNICAL SKILLS

Statistical Software: SAS, MATLAB

Databases: SQL Server, Oracle 11g, Teradata

Big Data Tools: Hadoop, Hive, Spark, Pig, HBase, Sqoop, Flume

Operating Systems: Windows 10/8/7

Data Visualization: Tableau 10/9

Languages: SQL, Python, C, JAVA, R

ETL: Data Integrator/ Data Services

Applications: Oracle SQL Developer, MS Word, MS Excel, MS Power Point, Teradata

WORK EXPERIENCE

Confidential, Austin, TX

Data Scientist/Analyst

Responsibilities:

• Part of a team to drive exertions around risk management, regulatory compliance, and operational efficiency.
• Applied machine learning techniques to identify best modelling approaches, and design, build and partnering to implement models that address the business problems.
• Resolved problems through various analytical techniques of machine learning, text mining, process mining, network analysis, and visualization.
• Worked on enormous amounts of data to enhance customer value or reduce non-credit losses.
• Identify and extract entity, and discover knowledge from structured and unstructured content.
• Applied different Machine Learning techniques for customer insight, target marketing, channel execution, risk management, and business strategy.
• Perform sentiment analysis and gathering insights from large volumes of unstructured data.
• Create multiple workbooks and dashboards using calculated fields, quick table calculations, Custom hierarchies, sets& parameters to meet business needs.
• Created different charts such as Heat maps, Bar charts, Line charts, etc.,
• Building, publishing and scheduling customized interactive reports and dashboards using Tableau Server.
• Visualize patterns, anomalies, and future trends by applying predictive analytic techniques.
• Communicate with team members, leadership and stakeholders on findings to ensure models are well understood and incorporated into business processes.
• Environment: Python, R, Tableau, Spark, Hadoop/Hive, Eclipse

Confidential, Reston, VA

Sr. Data Scientist/Data Modeler

Responsibilities:

• Build predictive models, Statistical analysis, and interactive dashboards to gain insights on what was driving performance in terms of reach, retention, and revenue growth
• Delivered numerous POCs that empowered network analysis, different GraphDBs, and MongoDB
• Applied advanced machine learning algorithms, including PCA, K-nearest neighbors, random forest, gradient boosting, neural network and xgboost
• PerformedDataAnalysis andDataProfiling using complex SQL queries on various sources systems including Oracle, Teradata.
• Developed Python modules for machine learning & predictive analytics in Hadoop on AWS.
• Developed spark streaming jobs using MLlib and deployed it working along the DevOps team.
• Designed and Developed Oracle PL/SQL and Shell Scripts, Data Import/Export, Data Conversions and Data Cleansing.
• Designed tables and implemented the naming conventions for Logical and PhysicalDataModels in Erwin r9.6
• Used Reverse Engineering and Forward Engineering techniques on databases and created tables and models indatamart,datawarehouse and staging.
• Created Mappings/workflows to extractdatafrom Excel file other databases and flat file sources and load into various Business Entities.
• DevelopedDataMapping, DataGovernance, Transformation and cleansing rules for the MasterData Management Architecture involving OLTP, ODS.
• Involved in SQL queries and optimizing the queries in Oracle10g, and Teradata.
• Deep knowledge on collaborative filtering approach.
• Worked Normalization and De-normalization concepts and design methodologies
• Documented Source to Target mappings as per the business rules.
• Successfully optimized codes in Python to solve a variety of purposes indatamining and machine learning in Python.
• Text Mining Packages under Python Programming to understand the frequent words for each category rating.
• Data Visualization using TABLEAU, ggplot2 package in Python.
• Delivereddatascience solution for a geo Location enrichment of socialdatavia API
• Updated Python scripts to match training data with our database stored in AWS Cloud Search
• Environment: Python 3.5.2, Tableau 8.x, Erwin 9.6, Oracle 12c, Teradata 15, SAS, NLTK, SVM (Support Vector Machine), JSON, XML, MapReduce, Spark, MLlib

Confidential, New York, NY

Data Scientist

Responsibilities:

• Managed Development of Enterprise Information Security Performance Measurement Reporting
• Developed Regulatory Monthly/ Quarterly Reports
• Developed Tableau Dashboard for Enterprise Security Reporting and Analytics
• Assess the data quality using python scripts and provide the insights using pandas 1.18.0
• Implemented R packages like dplyr for data manipulation
• Perform Extensive Data Analysis using tools such as Oracle/ SQL, Python, R, SAS impacting Enterprise Information Risk Team
• Environment: Oracle/ SQL, Python, R, SAS

Confidential, San Francisco, CA

Data Analytics Consultant - Master Data solution for Securities

Responsibilities:

• Collaborate with stakeholders to define functional and technical requirements for modeling Master Data
• Data exploration, Data Profiling, Data Quality and ETL to load and transform huge data sets.
• Data Profiling, Data Analysis; identify and implement business rules to uniquely identify Securities.
• Design and configure Match Rules and Trust Rules to cleanse, standardize, match and merge Securities records
• Designed and tested Predictive Algorithms using Historical Data
• Gathered and analyzed existing physical data models for in scope applications and proposed the changes to the data models according to the requirements.
• Custom Asset Classification using Python
• Environment: SQL Server, Erwin r9, SSIS, Informatica PowerCenter 9.6.1, IDQ, Informatica MDM, Python

Confidential, SFO, CA

Data Analyst

Responsibilities:

• Identified the most critical issues by performing quantitative analysis of Confidential feedback reports
• compiled performance data for the feedback reports ranging in value from 1.5 million to 2.2 million, which enables Confidential product teams to resolve priority issues earlier
• Utilized in-house software systems to provide analytical, presentation support for the management activities surrounding quarterly earnings and ad hoc monthly reports.