Sarath Tharayil

Sarath Tharayil Sreenivasan

Open to New RolesSheffield, UK--:--:--GMT

Data Scientist with commercial experience in analytics, strategy and sales and a master's degree in Data Science from the University of Sheffield. Previously at MuSigma (Business Analytics and Consulting). Ranked in top 10% of postgraduate cohort at the University of Sheffield.

Selected projects in data science, machine learning and NLP

Classification of AI-generated Human Faces
View Paper

Developed a novel architecture combining CNNs and Transformer networks for robust classification of AI-generated faces, achieving 83% accuracy. Implemented advanced data augmentation techniques and self-supervised pretraining using contrastive learning, improving model performance by 15% and validation accuracy by 12% on limited datasets.

Python logoPython
PyTorch logoPyTorch
Streamlit logoStreamlit
RAG-based Chatbot for Sentiment aware Document Retrieval
View GitHub

Designed and launched a Retrieval-Augmented Generation (RAG) chatbot leveraging LangChain for conversational orchestration and ChromaDB for semantic vector-based document retrieval. Integrated sentiment analysis using transformer-based models to adjust response tone and content based on user emotions, increasing user engagement metrics by 18% and reducing negative feedback by 22%.

Predictive Modeling of Building Energy Demand
View GitHub

Devised an ML model to predict building-level energy consumption using historical meter readings, weather patterns, and building characteristics from a public dataset of over 1,400 buildings. Incorporated time-series features like lag metrics, moving averages, and seasonal encodings to enhance model performance by 12%.

Predictive Maintenance for Industrial Equipment
View GitHub

Developed a predictive maintenance system for industrial equipment using sensor data and machine learning algorithms. Implemented real-time monitoring and anomaly detection to predict potential equipment failures.

Customer Churn Prediction
View Paper

Developed a machine learning model to predict customer churn with 92% accuracy. Implemented feature engineering and SHAP value analysis to identify key churn factors. Created an interactive dashboard for business stakeholders to monitor churn risk and take proactive measures.

Python logoPython
Scikit-learn logoScikit-learn
Pandas logoPandas
Last Played
Loading Spotify data…
Last Played
Loading Steam data…
© 2025 Sarath Tharayil. All rights reserved.