Sai Bhavani

Performed quantitative analysis and qualitative assessments on fair lending risk associated with HMDA Mortgage data, Developed compliance management reports to identify disparities in lending outcomes, Developed models for Pricing data of credit card data, Provided sample files for investigation of disparate treatment, Utilized software programs for compliance assessments and reviews, Performed statistical analysis for fair lending risks, Worked with business lines in identifying key data, Interpreted Statistical numbers to Senior Management

Performed quantitative analysis and qualitative assessments to identify the fair lending risk associated HMDA Mortgage data in accordance with the Fair Lending Standards
Developed compliance management reports that helped in identifying disparities in lending outcomes based on race, ethnicity, gender, and other protected characteristics
Developed models for Pricing data of credit card data to identify if there is any disparity in the pricing for protected groups
Developed Steering and Assistance Dashboard reports, Underwriting, Pricing and Counter Offer exception Dashboard reports for HMDA data to identify the disparity in lending outcomes for target groups
Provided business team with sample files for the identified focal points for the investigation of disparate treatment
Expertise in utilizing software programs such as SAS, RiskExec to perform thorough compliance assessments and reviews
Performed statistical analysis to identify fair lending risks using programming skills, regression analysis, statistical techniques for disparate treatment and impact testing
Worked with business lines in identifying and obtaining key data to be used in fair lending statistical analysis
Proficient in developing documentation for Models developed and in interpreting Statistical numbers to Senior Management
Knowledge of and experience in the Equal Credit Opportunity Act, the Fair Housing Act, CRA and other laws and regulations related to fair and responsible banking

Developed Risk Score models for AML data using logistic regression technique, Identified suspicious accounts and reduced false positives by 30%, Conducted feature and variable analysis, Created ETL jobs using SAS Data integration studio tool, Developed SAS DI Studio Jobs for data transformation, Created SAS ETL reports for risk rating and customer due diligence, Presented complex concepts in an easily understandable manner

Developed Risk Score models for AML data using logistic regression technique to predict the probability of money laundering associated with the retail banking accounts
Identified suspicious accounts, reduced false positives by 30% thus enhanced the decision-making for investigation process improving fraud detection accuracy
Conducted thorough feature and variable analysis to identify key predictors for the developed models
Performed various statistical analysis on the data to eliminate the variable with less predicting power
Worked with business teams in understanding the data and created ETL jobs using the SAS Data integration studio tool
Developed SAS DI Studio Jobs using Standard & User Written transformations for sourcing, transforming, and loading data between SAS and Oracle
Developed SAS ETL reports to identify when a Customers Financial Crime Risk rating (FCRR) and Customer Due Diligence (CDD) profile should be reviewed based on the trigger event generated
Created comprehensive model documentation, presenting complex concepts in an easily understandable manner non-technical people