Data Science Analyst

Rakshith Suresh

+1-562-***-**** ****************@*****.*** www.linkedin.com/in/rakshith-suresh/ https://rakshithsuresh.github.io/Portoflio/ EDUCATION

California State University, Long Beach, United States - Master, Information Systems (Data Science & Analytics) PES University, India - Bachelor, Electronics and Communications Engineering WORK EXPERIENCE

Bright Start Ed-Tech, United States - Data Science Analyst Nov 2024 — Present Learner Behavior Analytics: Analyzed learner behavior using Python and SQL, increasing course completion by 18% and generating

$80K+ in revenue through curriculum redesign strategies for targeted cohorts and regions. A/B Testing: Executed extensive A/B testing with SciPy and Statsmodels, reducing dropouts by 11% and improving engagement by 30% through optimized content strategies, email targeting, and testing variations. KPI Monitoring: Built interactive dashboards in Power BI using DAX, enabling KPI monitoring that drove a 30% increase in customer retention and proactive decisions with measurable insights across departments. Cross-Functional Collaboration: Collaborated with product, engineering, & design to embed insights, streamlining delivery efficiency. ETL & Segmentation: Engineered automated ETL pipelines using Python and SQL, transforming and modeling student data to identify untapped learner segments and boost engagement by 12% across varied learning modules. LTIMindtree Ltd, India - Data Analyst Aug 2021 — Jul 2023 Retail Forecasting & Optimization: Built SQL-based demand models using Snowflake and automation tools, cutting inventory waste by 22% and boosting shelf efficiency across supply chain hubs. Real-Time Sales Insights: Developed Tableau dashboards linked with AWS Redshift, enhancing KPI tracking and improving forecast accuracy by 10% for senior leadership across regional zones. Marketing Strategy & Segmentation: Designed marketing strategies using SQL and visualized segmentation in Power BI, driving 11x ROI on a $20M campaign and improving lead precision and conversion. Behavioral Clusterin: Applied clustering algorithms such as K-Means and DBSCAN to analyze churn and buyer behavior, increasing marketing efficiency by 25% and saving $85K annually in acquisition campaigns. Python Automation: Automated reporting with Python, reducing manual effort and enhancing speed, reliability, and global accessibility. Collaborative BI Enablement: Partnered with cross-functional teams to optimize Power BI dashboards, driving a 25% revenue increase through improved decision-making and insights.

ETL Acceleration: Automated ETL workflows using Snowflake, accelerating product rollouts & driving $50M+ in annual digital revenue. Data Analyst, Freelance Jan 2019 — Jun 2019

Logistics Dashboarding: Designed interactive dashboards using Excel, Matplotlib, and Seaborn to visualize logistics KPIs, enabling faster, data-driven decisions across nationwide delivery networks. Delivery Efficiency Optimization: Improved last-mile delivery by 25% through performance analysis using SQL and PostgreSQL, resolving bottlenecks across high-traffic regions and critical zones. Shipment Forecasting: Created forecasting models using Python and SQL, cutting transportation costs by 15% and enhancing SLA compliance and consistency across large freight operations. Fraud Detection & Risk Control: Built advanced anomaly detection models using Logistic Regression in Python, preventing $50K+ in fraud and reinforcing data integrity and robust risk control frameworks. System Integration: Collaborated with IT & logistics to deploy scalable analytics, boosting efficiency across distributed business systems. CERTIFICATIONS

Google AI Essentials Google Data Analytics Professional Certificate Google Business Intelligence Professional Certificate Introduction to Machine Learning Specialization PROJECTS

Bank Loan Analysis

Leveraged SQL and Power BI to analyze 38,600+ loan applications, identifying approval trends and default risks. Reduced defaults by 12% and improved approval efficiency using insights. Built dashboards to visualize risks, streamline workflows, and cut turnaround time by 25%.

Hospital Readmission Prediction

Built a Random Forest model in Python to predict hospital readmissions with 85% accuracy, helping flag high-risk patients. Reduced readmissions by 10%, saving $1M annually. Analyzed clinical data to optimize strategies, improving care quality by 15%. SKILLS

Data Science & ML : Python (Pandas, NumPy, Scikit-learn, Statsmodels), R, Random Forest, Logistic Regression, Clustering

(K-Means, DBSCAN), Time Series (ARIMA, SARIMA), Feature Engineering, A/B Testing, Hypothesis Testing, XGBoost

Data Analytics & BI Tools : Power BI, Tableau, Amazon QuickSight, Looker, Advanced Excel (Pivot Tables, Macros, Solver), VBA, KPI Dashboards, Storytelling with Data

Data Engineering & ETL : SQL (PostgreSQL, MySQL), Snowflake, Amazon Redshift, Google BigQuery, PySpark, AWS Glue, Apache Airflow, Data Cleaning & Transformation, Pipeline Automation Cloud & Dev Platforms : AWS SageMaker, AWS Lambda, Jupyter Notebooks, Excel Automation Data Management : Data Modeling, Dimensional Modeling, Data Warehousing Concepts, OLAP/OLTP, Star & Snowflake Schema, Query Optimization

Statistical Analysis &

Forecasting

: Descriptive & Inferential Statistics, Regression Analysis, Time Series Forecasting, ANOVA, Monte Carlo Simulation, Confidence Intervals, P-Values, Statistical Inference

Contact this candidate