Project Manager Data

XUANFU WU

* ********** **, *********, ** ***** 508-***-****(c)

*******@*******.***

SUMMARY:

. MS in Computer Science, strong coding skills in C++/Java with object-

oriented design and development.

. Experience in SQL, relational databases, data warehouse, OLAP, SAS,

Matlab, Perl and Shell scripting language.

. Deep knowledge in data mining, machine learning and predictive

modeling. Particularly in Decision Tree, Neural Networks,

Classification, Regression, Clustering, Numeric Analysis, Bayesian

Network, Optimization, Genetic Algorithm, Monte Carlo Simulation,

Agent-Based Modeling and Simulation, Collaborative Filtering,

Bootstrap and Ensemble method.

. Experience in data extraction, manipulation, algorithm design and

implementation.

SKILLS:

Languages : C/C++, Java, SQL, Mysql, PL/SQL,

Perl

Statistical tools : SAS, Matlab, SPSS, R, C5

Databases : Oracle, SQL Server 2000, MS Access,

Netezza, DB2, OLAP, ODBC

Operating Systems : Windows 2000/NT/98/XP, Linux, Unix

WORKING EXPERIENCE:

Analytic Consulting Group, Epsilon Inc., Wakefield, MA

Sr. Statistician

7/2008-present

Sr. SAS Programmer

7/2006-7/2008

Research Analyst

5/2005-7/2006

. Created macro tools for automated variable transformation/recoding,

automated model validation and scoring.

. Researched and determined appropriate statistical model, data mining

techniques as well as model fitting algorithms for various business

purposes.

. Assisted in data modeling, database design, and creation of logical

and physical data models in a database marketing environment.

. Designed and developed SQL and Perl/shell scripts to move and

transform data from multiple data sources to analytical database.

. Preformed data aggregation, summarization, and ad-hoc analysis using

NZSQL and SAS.

. Developed and tested automated analytic reporting and scoring

procedures.

. Developed SAS applications and Macros for data load, data

manipulation, data aggregation, data integration, data visualization

reporting such as graph, tables.

. Conducted EDA (exploratory data analysis) to the modeling dataset.

. Applied various model diagnostics techniques.

. Implemented Share-of-wallet (SOW) model using Markov Chain Monte Carlo

(MCMC) simulation, run the simulation, analyzed the data and presented

the results.

. Built acquisition, retention, up/cross-sell, attrition and consumer

lifetime value models using decision-tree, CART/CHAID, regression,

neural nets approaches.

. Conducted database marketing analysis in response analysis, ROI

analysis and customer profiling.

. Wrote Perl scripts to process input data and to perform data analysis.

. Researched and evaluated new analytical software/tools, such as R,

upgraded existing analytic/modeling tool kits to improve the

functionalities and efficiencies using C++, SAS.

. Designed and implemented programs and processes to standardize

statistical programming across projects.

. Provided technique and programming support for internal group and

external clients.

Business Intelligence & Decision Support Group, Bitpipe Inc., Boston, MA

Database Developer Intern

9/2004-1/2005

. Performed data extraction, transformation and load (ETL), built

dimensional and fact tables.

. Performed ah hoc query in SQL to support decision making process.

. Developed and implemented a recommendation system for the registered

users using collaborative filtering methods to improve marketing

performance.

Sociology Dept., Cornell University, Ithaca, NY

Matlab Programmer Intern

11/2002-2/2003

. Worked on the respondent-driven project to estimate group parameters,

implemented in Matlab.

Information Technology Dept., Union Pacific Railroad, Omaha, NE

Java Developer Intern

5/2002-8/2002

. Studied the concepts of agent-based modeling and simulation,

understood the Railroad's problem of allocating scarce network

resources for train service.

. Designed agent-based model to solve the business problem, built

software using agent-based modeling and simulation methods,

implemented in Java, Visual Caf , Swarm, and SQL.

. Presented the results to the group.

Horticulture Department, Cornell University, Ithaca, NY

Research Assistant

5/2000-12/2000

. Designed crop performance evaluation studies to estimate yield

difference under different locations.

. Performed data analysis using linear regression and logistic

regression.

Ministry of Agriculture, Beijing, China

Data Analyst

9/1991-12/1999

. Created and maintained crop database in MS Access, extracted,

transferred, loaded, summarized and analyzed data, and provided

monthly reports.

. Performed multivariate analysis to quantitatively assess the grain

yield and quality of newly crop varieties.

. Conducted crop variety performance trials, performed analysis of

variance.

Anhui Academy of Agriculture Science, Hefei, China

Research Assistant

9/1985-9/1991

. Conducted genetic studies to characterize virus resistance genes in

canola.

. Assisted project manager with experimental design, performed data

collection, and data analysis such as factor analysis and analysis of

variance.

EDUCATION:

. M.S. Computer Science, University of Nebraska, Omaha, NE

5/2004

Thesis: Developed and implemented an ensemble classification system

using decision tree and genetic algorithm, implemented in C++.

. B.S. Genetics and Plant Science, Beijing Agriculture University,

Beijing, China 7/1985

PUBLICATIONS:

Xuanfu Wu, Z Chen: Toward dynamic ensembles: the BAGA approach, ACS/IEEE

2005 International Conference on Computer Systems and Applications

(AICCSA'05) pp. 31-I

Xuanfu Wu, Z Chen: Recognition of exon/intron boundaries using dynamic

ensembles, 2004 IEEE Computational Systems Bioinformatics Conference

(CSB'04) pp. 485-486

Contact this candidate