Hi, I’m Keerthana Goka, a passionate data scientist and analyst with over 3 years of specialized experience in natural language processing, generative AI, and computer vision, combined with around 4 years in data visualization and statistical analysis. I love leveraging machine learning models and deep learning to solve complex problems and drive actionable business insights. Throughout my professional journey, I have developed a strong expertise in Python, SQL, and popular ML frameworks like TensorFlow and PyTorch, and I thrive in environments that challenge me to innovate, automate, and make data work for better decision-making and operational efficiency.

Keerthana Goka

Hi, I’m Keerthana Goka, a passionate data scientist and analyst with over 3 years of specialized experience in natural language processing, generative AI, and computer vision, combined with around 4 years in data visualization and statistical analysis. I love leveraging machine learning models and deep learning to solve complex problems and drive actionable business insights. Throughout my professional journey, I have developed a strong expertise in Python, SQL, and popular ML frameworks like TensorFlow and PyTorch, and I thrive in environments that challenge me to innovate, automate, and make data work for better decision-making and operational efficiency.

Available to hire

Hi, I’m Keerthana Goka, a passionate data scientist and analyst with over 3 years of specialized experience in natural language processing, generative AI, and computer vision, combined with around 4 years in data visualization and statistical analysis. I love leveraging machine learning models and deep learning to solve complex problems and drive actionable business insights.

Throughout my professional journey, I have developed a strong expertise in Python, SQL, and popular ML frameworks like TensorFlow and PyTorch, and I thrive in environments that challenge me to innovate, automate, and make data work for better decision-making and operational efficiency.

See more

Work Experience

Data Science Intern at Clark University
May 31, 2025 - August 5, 2025
Conducted research on predicting student attrition using machine learning frameworks including feature selection and class balancing with models like XGBoost, ANN, and Random Forest, resulting in a research acceptance at KDD2025. Developed an ECG image-denoising pipeline and MultiVision-enhanced CNN models employing pretrained ImageNet architectures, ensuring clinical interpretability with Grad-CAM, published at IEEE CAI 2025. Engineered a modular RAG-based chatbot leveraging LangChain, ChromaDB, and Hugging Face embeddings, integrating a 9B parameter LLM (Gemma-2) and optimizing retrieval methods for contextual accuracy. Explored Generative AI applications for academic content generation and summarization using transformer architectures to support automated educational assistance.
Network / Telecommunications Assistant at Clark University Information Technology Services
May 31, 2025 - August 5, 2025
Led a campus-wide VoIP migration covering 1,700+ phone extensions across 90 departments using Microsoft Teams Admin Center and Tableau dashboards for KPI tracking and user provisioning. Consolidated and cleaned address data for over 100 campus buildings, identifying discrepancies and advising executive leadership for improved planning. Automated network monitoring data extraction from SNMP and NetFlow tools, reducing manual analysis time by 50%, which enabled faster network issue detection and performance reporting.
Assistant Engineer (Data Scientist) at Greater Hyderabad Municipal Corporation (GHMC), India
December 31, 2023 - August 5, 2025
Built and maintained Tableau dashboards and GIS-integrated visualizations for real-time civic issue monitoring, improving resolution times by 40% and enhancing transparency for 500,000+ citizens. Used unsupervised learning (K-Means, DBSCAN) for municipal region segmentation aiding targeted infrastructure planning and service equity improvements by 30%. Collaborated with GIS teams integrating satellite imagery and location-tagged complaints to develop zone-wise cleanliness indices, reducing complaint resolution times by 20%. Developed predictive models with Random Forest and XGBoost to forecast vector-borne disease outbreak risks, improving resource allocation agility by 30%. Optimized complex SQL queries and database indexing to reduce data retrieval times by 35%. Led a GIS-enabled property tax collection pilot using vector mapping and LiDAR, managing a 40-member team and increasing tax revenue by 20%.
Assistant Engineer (Data Analyst) at Greater Hyderabad Municipal Corporation (GHMC), India
March 31, 2020 - August 5, 2025
Collaborated cross-functionally with 16+ departments to implement data-driven dashboards and workflows, enhancing operational transparency and decision-making. Cleaned and integrated over 1 million grievance records using Excel and SQL, improving data quality and reporting accuracy by 95%. Employed statistical techniques like regression and hypothesis testing to increase forecasting accuracy by 25%, supporting marketing strategy optimization. Automated weekly insights and reporting for multiple departments using Python and SQL, reducing analysis turnaround times by 50%. Redesigned the Birth and Death Registration system for 10M+ population, incorporating mobile login access for field officers, boosting accuracy and real-time tracking.
Data Science Intern, Data Science Program at Clark University
May 1, 2025 - August 5, 2025
Conducted research on predicting student attrition using machine learning models with feature selection and class balancing techniques. Developed an ECG image-denoising pipeline and proposed MultiVision-enhanced CNNs using pretrained ImageNet models with Grad-CAM interpretability to ensure clinical relevance. Built a modular RAG-based chatbot integrating Gemma-2 9B LLM with pipeline optimizations for contextual accuracy. Explored Generative AI techniques to build foundational academic content generation and summarization models leveraging transformer architectures to support educational automation.
Network / Telecommunications Assistant, Information Technology Services at Clark University
May 1, 2025 - August 5, 2025
Led a campus-wide VoIP migration impacting over 1,700 phone extensions across 90 departments using Microsoft Teams Admin Center and Tableau dashboards. Consolidated and cleaned campus address data from multiple sources to identify discrepancies and improve accuracy. Automated data extraction from network monitoring tools which reduced manual analysis time by 50%, enabling faster issue detection and performance reporting.
Assistant Engineer (Data Scientist), Information Technology Department at Greater Hyderabad Municipal Corporation (GHMC), India
December 1, 2023 - August 5, 2025
Built and maintained Tableau dashboards and GIS-integrated visualizations for monitoring civic issues improving resolution time by 40%. Applied unsupervised learning to segment municipal regions to help target underserved areas improving service equity by 30%. Collaborated on geospatial EDA integrating satellite imagery for maintenance prioritization, reducing complaint resolution time by 20%. Developed predictive models forecasting disease outbreak risk enabling proactive allocation of resources and reducing response times by 30%. Optimized SQL Server database efficiency through indexing, partitioning, and query tuning reducing data retrieval times by 35%. Led GIS-enabled property tax collection pilot project creating a 3D base map, managing a 40-member team and increasing tax revenue by 20%.
Assistant Engineer (Data Analyst), Information Technology Department at Greater Hyderabad Municipal Corporation (GHMC), India
March 1, 2020 - August 5, 2025
Collaborated with multiple departments to gather business needs and deploy data-driven dashboards improving transparency and decision-making. Cleaned and integrated over 1 million rows of grievance data with Excel and SQL improving data consistency by 95%. Applied statistical techniques enhancing forecasting accuracy by 25%. Automated weekly insights and visual reports increasing inter-departmental coordination and cutting analysis turnaround by 50%. Redesigned Birth and Death Registration system for 10M+ population adding mobile logins for field officers improving accuracy and accountability.

Education

Master of Science in Data Analytics at Clark University
January 11, 2030 - May 1, 2025
Master of Science in Data Analytics at Clark University
January 11, 2030 - May 1, 2025

Qualifications

AWS Certified Cloud Practitioner
January 1, 2024 - August 5, 2025
AWS Certified Cloud Practitioner
January 1, 2024 - August 5, 2025

Industry Experience

Education, Government, Healthcare, Life Sciences, Telecommunications, Software & Internet