Fraud Detection Data Scientist and Analyst

Mounika Chitturi

(***) ***- **** *****************@*****.*** Wichita falls, Texas LinkedIn

SUMMARY

Data Analyst with 4+ years of experience specializing in Fintech, Machine Learning, and Cloud ecosystems (AWS, Snowflake, dbt). Expert in developing Fraud Detection ML Pipelines (Python, XGBoost) and leading data governance for regulatory compliance. Proven track record in leveraging A/B Testing and advanced Time Series Analysis to drive quantifiable business value, including millions in averted losses and increased conversion rates. TECHNICAL SKILLS

Data Analysis & BI: SQL (PostgreSQL, MySQL, Snowflake), Advanced Excel, Power BI, Tableau, Looker, Google Data Studio, Mode Analytics

Programming & Scripting: Python (Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn), R (tidyverse, ggplot2, dplyr), PySpark Data Engineering & ETL: Apache Airflow, dbt, Apache Spark, AWS Glue, Azure Data Factory, Talend, SSIS Databases & Data Warehousing: Redshift, BigQuery, Snowflake, Databricks, Oracle, MongoDB Statistical & Quantitative Analysis: A/B Testing, Hypothesis Testing, Regression Modeling, Forecasting, Time Series Analysis, Statistical Inference

Machine Learning & Predictive Analytics: Feature Engineering, Model Evaluation, Supervised & Unsupervised Learning, ML Pipelines (Scikit-learn, XGBoost, LightGBM)

Fintech Domain Expertise: Payment Processing, Transaction Risk Analytics, Fraud Detection, Customer Segmentation, Credit Scoring, Regulatory Compliance (KYC, AML)

Software Development & Collaboration: Git/GitHub, Jira, Confluence, Agile/Scrum, CI/CD (Jenkins, GitLab CI), API Integration

(REST, GraphQL)

Cloud & Big Data Ecosystem: AWS (S3, Redshift, Lambda, Athena), Azure (Synapse, Databricks), GCP (BigQuery, Dataflow) Data Visualization & Storytelling: Interactive Dashboards, KPI Tracking, Executive Reporting, Data-Driven Insights Presentation EXPERIENCE

Data Analyst State Street, USA February 2025 – Present

• Developed and deployed a real-time Fraud Detection ML Pipeline using Python (Scikit-learn, XGBoost) on AWS SageMaker, achieving a 35% reduction in high-value fraudulent transactions and saving the firm an estimated $2.5 million in averted losses annually.

• Led a data migration and governance project for regulatory compliance, migrating 1.2 billion transaction records from Oracle to Snowflake and Redshift. This initiative utilized dbt for data transformation and reduced quarterly compliance reporting latency by 70%.

• Designed and executed a comprehensive A/B Test on the client onboarding platform, focusing on Credit Scoring workflow changes. Statistical analysis showed a statistically significant 12% increase in successful application conversion rate.

• Built an interactive, unified FinTech dashboard in Power BI/Tableau that consolidated key Payment Processing and risk KPIs

(e.g., Net Promoter Score, transaction volumes), which improved the executive team's decision-making speed by 20%.

• Created and optimized ETL jobs using Apache Airflow and PySpark to ingest and cleanse messy market data, improving data quality from 85% to 98% accuracy and providing analysts with 24-hour faster access to critical time series data.

• Conducted a predictive modeling project using Time Series Analysis on historical trading volumes, forecasting liquidity needs with 94% accuracy, which helped asset managers optimize capital reserves by $50 million. Data Analyst KPIT Technologies, India January 2019 - December 2022

• Built a process mining solution to analyze developer workflow within the Agile/Scrum framework, extracting data from Jira via API Integration and visualizing bottlenecks in Looker/Mode Analytics, which reduced average ticket cycle time by 18%.

• Automated the software release metrics reporting process by developing Python (Pandas) scripts and deploying them via GitLab CI/CD. This project decreased the weekly manual reporting effort from 8 hours to under 30 minutes.

• Executed a data quality improvement project on engineering logs stored in GCP BigQuery, identifying and resolving schema issues. This action reduced the data-related errors reported by the QA team by 40% in six months.

• Developed a proactive system failure forecasting model using basic Supervised Learning (Scikit-learn) on infrastructure and operational data, providing engineering teams with an average 2-hour lead time on critical alerts, reducing system downtime by 15%.

• Created a dynamic resource allocation dashboard in Google Data Studio, integrating data from AWS (Lambda, Athena) to track cloud spend vs. project velocity, directly leading to a $10,000 reduction in average monthly cloud infrastructure costs.

• Managed the data dictionary and governance for a core internal application, documenting 50+ key data entities in Confluence and enforcing SQL best practices, which improved cross-functional report consistency from 65% to 95%. EDUCATION

Masters in Business Analytics January 2023 - December 2024 Midwestern State University, Wichita Falls, Texas

Bachelors of Technology in Computer Science and Engineering July 2017 - July 2021 AVN Institute of Engineering and Technology, India CERTIFICATES

• Tata – GenAI Powered Data Analytics Job Simulation

• Deloitte Australia – Data Analytics Job Simulation

• Power BI – Udemy Certification

• Python – Task-Based Practical Training

Contact this candidate