Srilatha Adepu

Led research on intelligent automotive comfort systems, processing and analyzing 10M+ sensor data points; optimized data pipelines using Python, SQL, and ETL, reducing processing time by 50%.

Conducted exploratory data analysis (EDA) and applied statistical methods (A/B testing, hypothesis testing, regression) on physiological, sensor, and subjective feedback data to derive actionable insights.

Developed a machine learning–based personalized recommendation model using Multinomial Logistic Regression, integrating vital signals, environmental inputs, and user behavior for adaptive seat massage features.

Designed and deployed interactive dashboards using Power BI and Tableau, automating reporting workflows and enabling real-time KPI tracking for product performance and executive insights.

Collaborated with vehicle backend data engineering teams and utilized cloud platforms to extract and transform data from Automotive CAN signals, Energizing Comfort systems, and health monitoring applications.

Translated complex data into business insights by aligning with UX, R&D, and engineering teams, driving user-centric feature development through data visualization, BI reporting, and trend analysis.

Developed 10+ ETL pipelines and optimized data integration workflows using SQL and Power BI, improving data quality by 30% and reducing reporting errors by 40%.

Conducted predictive and descriptive analytics on 50M+ records across Retail, Healthcare, and E-Commerce, contributing to a 15% increase in revenue through data-driven strategies.

Designed and maintained 15+ interactive dashboards in Power BI, enabling 100+ stakeholders to monitor KPIs in real-time, which accelerated decision-making by 25%.

Collaborated with business teams to translate data into actionable insights, enhancing operational performance and aligning analytics with strategic goals.

Developed and maintained 20+ automated Power BI reporting solutions using DAX, Power Query, and SQL, enabling real-time tracking of Forex and Remittance KPIs, which improved reporting speed by 25% and supported faster business decisions.

Extracted and transformed data from cloud-based banking systems and internal databases, building robust ETL pipelines to cleanse, standardize, and integrate 1M+ customer transaction records.

Created interactive dashboards and operational reports that enhanced transparency in currency exchange, remittance trends, and vendor performance, leading to a 20% improvement in operational efficiency.

Automated recurring reporting tasks with SQL and Python, reducing manual effort by 30%, minimizing errors, and supporting compliance and audit readiness through centralized BI reporting.