Data Scientist - Predictive ML & Analytics

Varshini Yanala

Data Scientist

Charleston, IL (Open to Relocate) +1-217-***-**** ***************@*****.*** LinkedIn SUMMARY

Data Scientist with 3+ years of experience developing machine learning models, statistical analyses, predictive solutions, and analytical datasets using Python, SQL, and cloud data platforms. Experienced in feature engineering, exploratory analysis, model evaluation, forecasting, financial analytics, and data visualization across customer, transaction, portfolio, and operational datasets. Skilled in Scikit-learn, XGBoost, Pandas, NumPy, PySpark, Snowflake, Databricks, Power BI, Tableau, and Generative AI for analytical applications. SKILLS

Programming & Data Science: Python, SQL, Pandas, NumPy, PySpark, Scikit-learn, Data Cleaning, Data Transformation, Exploratory Data Analysis, Feature Engineering

Machine Learning: Machine Learning, Supervised Learning, Predictive Modeling, Regression, Classification, XGBoost, Random Forest, Model Training, Model Validation, Model Evaluation, Feature Selection Statistics & Analytics: Statistical Analysis, Descriptive Statistics, Hypothesis Testing, Correlation Analysis, Regression Analysis, Statistical Modeling, Time Series Analysis, Forecasting, Trend Analysis, Predictive Analytics Data Visualization: Power BI, Tableau, Matplotlib, Seaborn, DAX, Dashboard Development, KPI Analysis, Interactive Dashboards, Data Storytelling SQL & Data Management: Advanced SQL, CTEs, Joins, Subqueries, Window Functions, Aggregations, Query Optimization, Data Validation, Data Reconciliation, Data Quality

Cloud & Data Platforms: Snowflake, Databricks, Azure Data Lake, Microsoft Azure, SQL Server, PostgreSQL, MySQL, ETL, Data Integration, Data Warehousing, Data Modeling

AI & Generative AI: Azure OpenAI, GPT Models, Generative AI, LLMs, Prompt Engineering, Natural Language Querying, AI-Assisted Analytics, AI-Based Data Analysis

Business & Financial Analytics: Financial Analytics, Portfolio Analytics, Investment Analytics, Customer Analytics, Transaction Analytics, Risk Analytics, Banking Analytics, Operational Analytics, KPI Analysis WORK EXPERIENCE

Charles Schwab, USA Data Scientist Jan 2026 – Present

Developed XGBoost predictive models using Python, SQL, and engineered behavioral features across 5M+ investor records, identifying portfolio and engagement patterns for client analytics.

Analyzed investor and portfolio datasets with Pandas, NumPy, SQL, and statistical methods, identifying 20+ behavioral drivers that informed product, investment, and client strategies.

Engineered modeling datasets using Python, SQL, Snowflake, and Databricks, reducing data discrepancies by 28% while standardizing investor, portfolio, transaction, and engagement attributes.

Evaluated classification models using feature importance, validation metrics, and cross-validation techniques, improving client engagement prediction accuracy by 22% across investment analytics datasets.

Performed statistical analysis, trend analysis, and forecasting on investor activity and portfolio performance, translating analytical findings into actionable insights for finance and product stakeholders.

Built Power BI dashboards combining model outputs, portfolio metrics, and client behavior indicators, reducing recurring analytical reporting effort by 30% for cross-functional stakeholders.

Automated Python and SQL data preparation workflows, saving 12 hours monthly while improving reproducibility and consistency across recurring financial analysis, modeling, and reporting processes.

Applied Azure OpenAI and GPT models to financial analytics workflows, reducing information retrieval time by 40% across 8+ initiatives while collaborating with product, finance, and technology teams. Coforge, India Data Scientist Feb 2022 – Jul 2024

Developed predictive models using Python, SQL, and statistical techniques across lending and payment datasets, analyzing customer behavior, transaction activity, and operational performance.

Performed exploratory data analysis across financial datasets, identifying 20+ customer, transaction, and operational drivers that supported lending performance, risk analysis, and business planning.

Engineered feature preparation workflows using Python, SQL, and Pandas, improving data quality by 27% across financial modeling datasets used for recurring analytical processes.

Built forecasting workflows using statistical modeling and time series analysis to evaluate lending trends, transaction volumes, customer activity, and operational performance for business planning.

Optimized SQL queries using joins, CTEs, aggregations, and window functions, reducing execution time by 45% across large financial and transaction datasets.

Automated Python and SQL analytical workflows, saving 16 hours monthly while standardizing recurring data preparation and improving delivery consistency for financial reporting outputs.

Investigated transaction and lending anomalies using statistical analysis and root-cause techniques, reducing recurring data and process issues by 25% while visualizing findings in Power BI and Tableau. PROJECTS

Customer Churn Prediction & Behavioral Analytics Python, Pandas, NumPy, Scikit-learn, XGBoost, SQL, Power BI

Developed a customer churn prediction model using Python, SQL, Pandas, and XGBoost, engineering behavioral features to identify customer segments associated with elevated attrition risk.

Evaluated classification performance using precision, recall, F1 score, and confusion matrices while building Power BI dashboards to analyze churn drivers and retention patterns.

Analyzed customer behavior across demographic, transaction, and engagement attributes, translating model findings into actionable segments for targeted retention and customer experience analysis. Financial Transaction Risk & Anomaly Detection Python, SQL, Pandas, NumPy, Scikit-learn, XGBoost, Power BI

Analyzed 1M+ financial transaction records using Python, SQL, and statistical techniques, identifying transaction patterns, behavioral anomalies, and risk indicators across customer activity.

Engineered transaction level features and applied machine learning techniques to evaluate anomalous behavior, supporting risk segmentation and analytical investigation across financial datasets.

Developed Power BI dashboards presenting transaction trends, anomaly patterns, customer segments, and model findings to support financial risk analysis and stakeholder decision making.

EDUCATION

Masters of Science in Computer Technology Eastern Illinois University, Charleston, IL, USA Aug 2024 - May 2026

Contact this candidate