Saurabh P
Mangalore
Summary
A highly accomplished Senior Data Scientist at Nielsen, I am committed to driving innovation and growth within organizations. With expertise in data analysis, predictive modeling, and machine learning, I deliver actionable insights that consistently lead to measurable business outcomes. As a collaborative team member, I thrive in dynamic environments where I can apply my skills to develop data-driven strategies, streamline processes, and enhance decision-making quality.
Overview
2026
2026
years of professional experience
Work History
Senior Data Scientist
Nielsen
Bangalore
2021 - Current
- Led cross-functional execution of complex fusion projects, delivering high-impact media insights to clients, including HBO, ABC, NBA, MSNBC, NBC, Carat, and Scripps Newsy, significantly influencing their data-driven decision-making.
- Contributed to research and development projects for HBO Max, leveraging expertise in data mining, data structures, data analysis, and ML algorithms.
- Guided and trained a team of four members, and helped set up five fusion projects involving exploratory data analysis, data extraction using Databricks, data analysis, visualizations (Power BI), and machine learning for clients such as Apple, ESPN, Carat, NBA, MSNBC, and NBC Olympics.
- Developed code to generate YAML configuration workbooks, helping reduce reliance on Excel, and offering a more accessible solution for team members without Excel licenses.
- Implemented custom data transformers for the Starship library using PySpark to support smooth and efficient data processing.
- Enhanced code efficiency by developing pipeline-based code for two projects using the Starship library, monitored through Airflow.
- Contributed to the Long-Term Reach initiative by designing deduplication algorithms for viewer-level data,
enhancing the accuracy of audience metrics. - Collaborated with ETAM and the Thailand team to generate weekly reach and rating reports for the Thailand market, finetuning duration and prime-time calculations within the code.
Data Science Intern
Seceon
Varanasi
2020 - 2021
- Analyzed large datasets to identify trends and patterns.
- Collaborated with team members to design data visualizations for presentations.
- Conducted in-depth research on various cyber attacks and the ML algorithms for detecting the actual threats and triggering an event, then found remedies to stop this threat.
- Worked on the ML algorithm and EDR event testing and debugging the defects using Cassandra and Elasticsearch.
QA Analyst
99 Games Robosoft Technologies
Udupi
2017 - 2019
- Led QA testing across Android, iOS, and Facebook platforms.
- Used SQL and DeltaDNA for game performance analysis.
- Collaborated on bug tracking and testing workflows through API analysis.
Education
PG Diploma - Data Science
Manipal University
01-2020
Bachelor of Engineering - Electrical, Electronics And Communications Engineering
Canara Engineering College
01-2017
Skills
- Data analysis
- Machine learning
- Statistical modeling
- Generative AI
- Cross-functional team collaboration
- Solution architecture design
- SQL database management
- Data visualization
- Statistical analysis
- Predictive modeling
- Business intelligence solutions
- Deployment
Projects Undertaken
Document intelligence and chat portal using advanced RAG
- Objective: Built a full-stack AI-powered platform for document analysis and intelligent chat using advanced retrieval-augmented generation (RAG), enabled semantic search, single/multi-doc QnA, and document comparison capabilities.
- Techniques applied: LangChain, Hugging Face, OpenAI, BGE, FAISS, Chroma, Pinecone, FastAPI, Streamlit, vLLM, Groq, PyMuPDF, Docker, GitHub Actions, AWS (ECR, Fargate, IAM, Secrets Manager), and SonarQube
- Impact: reduced manual document review time by 70%, enabled real-time QnA from PDFs and Word docs, and deployed a scalable solution with CI/CD automation, and cost-effective AWS Fargate deployment
Technical Skills
- Language and libraries: Python, SQL, Numpy, Pandas, TensorFlow, Pytorch, Scikit-Learn, Matplotlib, Seaborn, Flask, Streamlit, FastAPI, etc
- Machine Learning: Linear-logistic regression, decision tree, SVM, KNN, random forest, dimensionality reduction, K-means, naïve Bayes, ridge-lasso, DBSCAN, time series forecasting, bagging, boosting, XGBoost, etc.
- Deep Learning: ANN, CNN, natural language processing, GEN AI, activation function, SHAP, LIME;
- MLOps: version control (Git), building pipelines, experimentation methods (DVC/MLFlow), CI-CD (Git Actions, CircleCI, TravisCI), containerization (Docker), deployment (AWS)
- AWS: IAM user, ECR, EC2 servers, AWS Lambda, S3, AWS SageMaker
- Other: Statistics, Tableau, Atlassian Suite, EDA, Google Workspace, MS Suite, MS Excel
Achievements
- Received Simply Excellent - Growth (Gold) award for leading cross-functional execution of complex fusion projects, and guiding a team of four to deliver high-impact insights for clients like HBO, NBA, MSNBC, and NBC
- Received simply excellent growth (silver) award for enhancing code efficiency by implementing PySpark transformers, Airflow pipelines, and a custom YAML configuration tool that reduced team reliance on Excel
- Received a simply excellent growth (silver) award for contributions to R&D projects for HBO Max and the long-term reach initiative, specifically for designing viewer-level deduplication algorithms to improve metric accuracy
Timeline
Senior Data Scientist
Nielsen
2021 - Current
Data Science Intern
Seceon
2020 - 2021
QA Analyst
99 Games Robosoft Technologies
2017 - 2019
PG Diploma - Data Science
Manipal University
Bachelor of Engineering - Electrical, Electronics And Communications Engineering
Canara Engineering College