SUMMARY

• Data scientist with a double master’s degree in Financial Math and Management.
• Excelled in 3 years professional experience in the finance industry and multiple programming languages.
• Enthusiastic about implementing Data Science techniques to solve challenging problems.
• Adept at teamwork in fast - paced environments.

PROFESSIONAL EXPERIENCE

Data Scientist

Confidential, San Francisco, CA

Responsibilities:

• Immersed in an intensive data science program covering statistical analysis, machine learning, model design, and working with data at scale. Applying data science advanced techniques to solve real-world problems.
• Agile methodology was used throughout the project and had daily scrum meeting and bi-weekly sprint planning and backlog meeting.
• Extensively involved in almost all the phases of Project Life Cycle (SDLC) right from Requirements Gathering to Testing and Implementation, Reporting etc.
• Learned the company’s EDW architecture which consists of sources, middleware, staging area, data warehouse, and reporting tools.
• Worked on data profiling & various data quality rules development using Informatica Data Quality.
• Implemented Exception Handling Mappings by using Data Quality, data validation by using Informatica Analyst.
• Build and developed reports based on the user stories given by the product manager and product owner.
• Held responsibility for integration points and the order in which these must be executed.
• Built compelling, interactive dashboards inTableauthat answer key business questions
• Evaluated DataMart’s for the tableau visualization.
• Created extracts from the data source and refresh extracts on the monthly data.
• Used data blending, groups, sets, dual axis, and synchronized axis to enhance the data visualization.
• Implemented Change Data Capture using Informatica Power Exchange 9.1.
• Designed, developed Informatica Power Center 9.5 mappings to extract, transform and load the data into Oracle 11g target tables.
• Extensively worked on Informatica tools like source analyzer, mapping designer, workflow manager, workflow monitor, Mapplets, Worklets and repository manager.
• Used Type 1 SCD and Type 2 SCD mappings to update slowly Changing Dimension Tables
• Used Debugger in Informatica Power Center Designer to check the errors in mapping.
• Created test cases and completed unit, integration and system tests for Data warehouse.
• Wrote SQL, PL/SQL, stored procedures for implementing business rules and transformations.
• Involved in Performance tuning for sources, targets, mappings, sessions and server.
• Closely moved with the Micro strategy reporting team and helped them to get the data for creating report.
• Used dashboard actions for the drill down of various reports and URL action to connect to the tableau server.
• Published reports from the tableau desktop to the tableau server and also managing the sites and projects on the tableau server.
• Creating user filters on the reports and restrict the data and the visualization based on the user requirements.
• Managed different server such as production server, Development Server and QA Server.
• Created Proof of concepts for the different user in the tableau server.
• Used JavaScript API for the deployment of the visualization in the HTML Page.
• Prepared an ETL technical document maintaining the naming standards.
• Created deployment groups in one environment for the Workflows, Worklets, Sessions, Mappings, Source Definitions, Target definitions and imported them to other environments.
• Advanced coursework in machine learning, statistics, data engineering (Scala, Spark, Map Reduce), and Python for data science (SQL, NLP, MongoDB, Pandas, Scikit-Learn, Tableau, Matplotlib).
• Capstone Project: Movie box office predictor. Predict second week box office based on movies' public information. With data of over 10,000 movies, built multiple linear regression models with ridge regularizations.
• Case Study: NY Times articles analysis using TFIDF with Scikit-Learn and NLTK. Build a text processing pipeline, including tokenization, stripping stopwords, and stemming. Use tf-idf and cosine similarity to compare documents.
• Case Study: Predict auction prices of heavy machinery with linear regression, SVMs, and feature engineering.
• Case Study: Churn predictor of a private driving service application with logistic regression and SVMs.
• Case Study: Joke recommender with Graphlab.
• Case Study: Fraud detection predictor with logistic regression and ensemble methods.

Environment: Informatica Power Center 9.5, Informatica Power Exchange 9.1, Informatica Data Quality (IDQ) 9.5, Informatica Analyst, Informatica MDM Multi-Domain 10.0, IDD/BDD, Oracle 11g, PL/SQL, SQL, Flat Files, TOAD, Unix, SQL Server 2012.Tableau Desktop 9, Tableau Server 9, TabCmd, IDM DB2, Data Studio 2010 UNIX script, Java, Net Beans, Oracle, SharePoint, Microsoft Excel, HTML, XML.

Branch Operations Manager

Confidential

Responsibilities:

• Data analysis for private and business clients. From clients’ basic information, cash flow and daily business transactions data, predicted future cash flow, improved customer experience, created annual budgets over $30 millions, and supervised the implementation.
• Issued Bank’s Acceptance Bills. Introduced SQL technique to the old routine and lowered 75% labor cost.
• Supervised 20 tellers’ duties including ordering currency from Federal Reserve, foreign currency purchase and sale, and change order processing. Coordinated with multiple departments.

Data Analyst

Confidential

Responsibilities:

• Analyzed tomato yields data from 2007, to study the outcome of different grafting techniques and fertilizers.
• Designed a model with longitudinal factors and macro using SAS, and proposed suggestions.