We provide IT Staff Augmentation Services!

Data Scientist Resume

0/5 (Submit Your Rating)

NY

SUMMARY

  • Master’s degree with 5+ years of extensive experience in SAS programming, Python and data analytics using various analytic, statistical, reporting and Business Intelligence (BI) tools.
  • Extensive experience of building software systems and being part of every phase of the Software Development Life Cycle (SDLC), managing and understanding business needs and consistently meeting critical deadlines and providing efficient solutions in all types of fast paced environments.
  • Significant experience in requirement gathering, building, designing and testing the application to meet the functional Design and Business Process Design.
  • Strong experience with databases like Oracle, Teradata, MS SQL Server, DB2 and MS Access.
  • Expertise in using various SAS report generating procedures like PROC REPORT, PROC FREQ, PROC TABULATE, PROC MEANS, PROC SUMMARY, PROC APPEND, PROC TRANSPOSE, PROC EXPORT, PROC IMPORT, PROC FORMAT, PROC UNIVARIATE, MERGE and SET statements.
  • Hands on experience in SAS programming for extracting data from Flat files, Excel spread sheets and external RDBMS (ORACLE) tables using LIBNAME and SQL PASSTHRU facility.
  • Solid statistical background with experience in diverse set of procedures but not limited to methods such as Classification algorithms, Multivariate regression, Cluster analysis, Decision Trees, Random Forests, Neural Nets, NLTP(Natural Language Text Processing).
  • Skilled in using SAS Statistical procedures like PROC CORR, PROC GLM, PROC ANOVA, PROC LOGISTIC, PROC FACTOR, PROC PRINCOMP AND PROC DISCRIM.

TECHNICAL SKILLS

Operating Systems: UNIX - Shell Scripting, MS Windows

Language: SAS, SQL, Python, R

SAS Tools: SAS/Base, SAS/Macro, SAS/SQL, SAS/Forecast, SAS/Connect, SAS/ODS, SAS/ACCESS

Database: MS-Access, Oracle, SQL server

Other Technologies: Tableau, Google Analytics, Gephi, Weka, DI Studio, Microsoft Office (Word, Excel, PowerPoint, Outlook)

PROFESSIONAL EXPERIENCE

Confidential, NY

Data scientist

Responsibilities:

  • Liaison between business units throughout internal and external Clients and the Product Team.
  • Executing Direct Mail Campaigns: Initiated ETL processes for databases to extract data and ensure compliance running it through standard waterfalls, scoring and QCing the data and performing selections to Confidential a population with the least risk and high predictiveresponse rate.
  • Analyzed email marketing data and social media data from various resources using web analytics/ text analytics in Python.
  • Post campaign analysis: Performing model validation and analysis through k-folds Cross-Validation, Leave-One-Out-Cross Validation (LOOCV) on how creative tests and data tests have performed in campaigns, and making business recommendations based on analysis to maximize ROI.
  • Undertaking forecast of returns through the AR and ARIMA models of financial time series using SAS/Forecast in Enterprise Guide.
  • Giving recommendations on campaign design to ensure key objectives are measurable (Churn / ROI / Product adoption)
  • Built a propensity model to predict churn - achieved an accuracy rate of 95%+
  • Extensively using SASto extract data, manipulate data for analysis and to generate summarized reports at monthly basis.
  • Deploying statistical modeling techniques like variable selection, Logistic regression, clustering, ANOVA, and neural networks to ensure that we are targeting the appropriate customer base at right time.
  • Following System Development Life Cycle (SDLC) methodology for the design, development, implementation and testing of various SAS modules.
  • Supporting and training other members of the analytical team when required.

Environment: SAS/BASE, SAS/MACRO, SAS/ETS, SAS/CONNECT, SAS Enterprise Guide, Python ORACLE, SQL Server, Tableau, UNIX

Confidential, NY

Data Analyst

Responsibilities:

  • Systematically derived mathematical expressions for computing many common loan performance metrics and analytics from loan behavior state transition models and loss severity models.
  • Coded and tested SAS modules that do all these computations
  • Conducted model performance tracking analyses and reporting for FAS114 book with model error impact analysis on Net Present Value for business stakeholder and Model Risk Management
  • Tracked loss severity model by developing SAS modules, reconciling computation details with modelers and building tracking reports
  • Coded SAS algorithm to attribute integrated metric errors to component model errors and analyzed model error compounding issue
  • Compared projection of different loan performance models, helped reconcile on data profile, core transition rates, marginal/conditional prepayment default and repurchase rates and loss severity
  • Carried out ad hoc analysis to support various business purpose including: (1) Implemented fair comparison by controlling key risk dimensions for MBS Policy to compare loan performances of re-performing loans with performing population; (2) Computed MBS loss distribution for Model Oversight Committee; (3) Computed and analyzed Loss distribution across Single Family Loan Level Pricing Adjustment grid related to Johnson-Crapo Reform Bill; and etc.
  • Applied parallel processing in SAS and created SAS modules to deal with big mortgage data set
  • Followed System Development Life Cycle (SDLC) methodology for the design, development, implementation and testing of various SAS modules.

Environment: Base SAS, SAS/ODS, SAS/Macros, SAS/Access, SAS/Connect, SAS/Graph, SQL Server, Oracle, Tableau, UNIX, SAS/SQL, MS Excel

Confidential, MN

SAS Programmer

Responsibilities:

  • Developed centralized inventory/replenishment planning and forecasting system-using SAS.
  • Led inventory analytics team in statistical modeling, business case development and reporting activities.
  • Extracted and cleaned data from multiple types of sources including plain textfiles, Excel spreadsheets, pdf documents, and Microsoft SQL databases for use in quality analytics models Worked on data validation, cleaning and transformation using PROC SQL queries and SAS Macros.
  • Evaluated the dataset by performing dimension reduction, regression and clustering before forecasting.
  • Created time series forecasting models using historical data and external information for all product families to predict store sales in the forthcoming year.
  • Included attributes like Holiday sales, Fuel-prices, CPI, store size and store location for an extensive study.
  • Utilized PROC FORECAST to generate exponential smoothing model using the ARIMA procedure
  • Utilized the model for demand planning purposes as well as inventory optimization for balancing inventories costs, planning resources and customer service levels.
  • Forecast accuracy improved over 14% from time of implementation; in turn this improved service levels and retail sales.
  • Created and distributed forecastingreports, as well as POS reports, and performed value-added analysis.
  • Identified and implemented ways of improving data collection, forecast accuracy, and reporting processes.

Environment: Base SAS, SAS/Macro, SAS Forecasting tool, SAS/Graph, SAS/Stat, SAS/SQL, SAS/Access, UNIX

Confidential, NJ

SAS Programmer

Responsibilities:

  • Initiated ETL processes for databases to extract data and ensure compliance.
  • Performed customer segmentation using cluster analysis and used self-organising maps to visualize and interpret the clusters.
  • Developed advanced predictive models using Logistic Regression and Decision Trees in SAS around insurance premiums, customer lifetime value, customer buying behaviours to predict default.
  • The advanced modeling technique helped reduce forecast variance from 6.5% to 4.8%.
  • Performed time-series analysis to assess customer value and their impact in generating profits.
  • Designed and implement targeted initiatives to those customers who are most at risk of destroying the value of the business by accounting for lapse probability, value and segment.
  • Designed incentives that would appeal customers based on data insights. Divided customers into segments of- targeted marketing, customer-retention, debt-recovery and cross-sell.

Environment: Base SAS, SAS/Macro, SAS Forecasting tool, SAS/Graph, SAS/Stat, SAS/SQL, SAS/Access, Oracle, SQL Server, MS office tools, Windows.

We'd love your feedback!