o Part of GRA-Wholesale Risk Analytics team which is responsible for developing commercial credit risk rating scorecards by logistic regression in SAS for Bank of America portfolio and to define emerging risk assessments, credit risk scenario analysis, as well as risk modeling using suitable machine learning algorithms to support bank in establishing risk management policies, limits, standards, controls, metrics, and thresholds.o Presented detailed reports about the meaning of gathered data to senior management and regulators and help them identify scenarios utilizing modifications in the data.o Gathered, cleaned, and reconciled large commercial credit data sets to support corresponding credit risk analyses and ad/hoc requests arising from evolving topics of concern to upper management, providing factual illustrative metrics and views for broader socialization.o Technical guidance and strategic recommendations regarding data-related decisions/projects.o Assessed, monitored, and forecasted wholesale credit risk, providing insights and recommendations on how to mitigate it.

o Part of Financial Crimes & Analytics teams which is responsible for developing Automatic Detection Channel Platform application to build scenarios over Bank financial transactions.o Involved in understanding the Requirements of the End Users and Developed Strategies for ADCP Scenario development.o Developing ADCP scenarios in SAS and Teradata over financial transactions to identify transactions with potential financial fraudulent/crime.o Conducted analysis on customer and transactional data to make determinations of irregular activity and behavior patterns or customer profile changes through an understanding of industry norms, historical customer activity, and regulatory definitions of suspicious activity.o Developed control reports using SAS and Teradata to generate alerts for Suspicious Activity Report (SAR) for downstream systems.o Performed Gap and Impact analysis and present findings and proposals of analysis to team members and senior stakeholders.

o GRA-Wholesale Risk Analytics teams which are responsible for developing commercial credit risk rating scorecards by logistic regression in SAS for Bank of America portfolio and also to also define emerging risk assessments, credit risk scenario analysis, as well as risk modeling using suitable machine learning algorithms to support the bank in establishing risk management policies, limits, standards, controls, metrics, and thresholds.o Cleaned, Transformed and loaded historical financial statement data to build commercial loan portfolio and conducted factor analysis, sensitivity analysis, Binomial distribution, population stability, Internal Benchmarking, and scenario testing to access the model performance. o Successfully built and validated the correctness cohort time-series version of the commercial loan portfolio to track the performance of all risk rating scorecards.o Designed factor analysis, sensitivity analysis, Binomial distribution test, Population stability and Scenario testing using SAS 9.4 for determining statistical appropriateness of commercial risk ratings scorecard models used in Forecasting, Regulatory Capital, and Portfolio Industry Growth Strategy. o Research and analysis to provide a micro view of risk management in a particular business line and a macro view of risk management.o Research and Invest to identify the root cause and provide a fix for any data quality issues in portfolio data.o Researched various Adhoc requests/issues from LOB managers and risk management and created dashboards and graphs using SAS for providing insights on my analysis.o Ensured compliance with government regulations regarding Bank of America’s GRA Risk scorecards. Resolved RAI’s raised from Model Risk Management (MRM) team for regulatory requirements.o Involved in developing emerging risk assessments, credit risk scenario analysis, as well as risk modeling using suitable machine learning algorithms.

Overview: Building packages to integrate data related to Priceline bookings, Emergency road services (ERS) and Trip-tik from source-system into AAA Carolinas new Salesforce systems.Environment: SQL Server Integration services 2012 (SSIS), MS SQL Server 2014, T-SQL, Windows 7, MS Office, SQL Server Agent, IBM Cognos.

Overview: The scope of this project is related to Credit Risk Management(CRM), working on customer’s data including origination and performance data to effectively develop recommendations. Used customer’s portfolio data along with various products information like debts, credits, collateral, equity, shares, and bonds and develop insights on the customers performance. Worked on customer historic Data by comparing current month data and previous month data or going back up to 6 years to check the same month’s data to reveal the similarities and variances in the data. The determination is usually based on checking differences in missing, mean, standard deviation, minimum and maximum values of the range of data. Environment: SAS Enterprise Guide, SAS Base, SAS Macros, MS SQL Server, SQL Server Integration services (SSIS), Windows 7, MS Office including Excel, Unix, SQL.

Overview:This project involves in building a Data warehouse for Telecom client which stores the retailers and distributor sales transactions and their hierarchies which is further useful for calculation of Key Performance Indicators (KPIs) for commissions and incentives for retailers and distributors. Extracting the raw data from flat files and load the data into data-warehouse by applying Source to Target mapping and transformation rules for consolidation of retailer and distributor transactions and design of operational and analytical reports and dashboards.Environment: Informatica 8.6.1, MS SQL Server, Windows 7, MS Office, HP Quality Center, Unix shell scripting.

Client: SFR (A French Telecom)Overview: Analysis over customer billing and usage data warehouse to generate variety of reports on usage and performance for clients business team. Implemented various reports helping to gather insights into the duration of usage activities to provide key metrics which drivers potential improvements.Environment: Informatica 8.6.1, Tableau, MS SQL Server, Windows 7, MS Office, HP Quality Center, Unix shell scripting.