Thippesh Mugalikatte Siddappa

Skilled Data Scientist and ML Engineer with 5+ years of experience in leveraging advanced machine learning to solve complex business problems. Proficient in programming languages such as Python and R, with extensive experience using libraries including Pandas, NumPy, Matplotlib, Sci-kit Learn, TensorFlow, Keras, and PyTorch to build predictive models and data solutions. Expertise in Machine Learning Algorithms like Logistic Regression, Linear Regression, Naive Bayes, K-NN, Decision Trees, SVM, PCA, Boosting Algorithms, and Clustering techniques (K-means, Hierarchical Clustering).

Led projects implementing Generative AI technologies like Gemini, Llama, and OpenAI for building intelligent conversational agents and chatbots. Extensive experience in Deep Learning with a focus on Neural Networks and advanced modeling algorithms to drive complex decision-making processes. Specialized in Natural Language Processing (NLP), including NER, TFIDF, Regex, Gensim, Hugging Face, TextBlob, and Google Translate, enabling insightful analysis from unstructured text data.

Adept at using Cloud Technologies (primarily GCP) for deploying AI models and managing large-scale data processing tasks in cloud environments. In-depth knowledge of Big Data Technologies including Hadoop, Spark, and Pyspark, and building scalable data pipelines for real-time data processing. Skilled in Data Flow & Mining techniques, including ETL, Data Wrangling, and designing data flow architectures to streamline data ingestion and transformation processes.

Proven ability in optimizing SQL queries and working with databases like MySQL and MongoDB to efficiently store and query large datasets. Experienced in creating real-time dashboards and data visualizations with tools like Tableau to provide actionable insights to business stakeholders. Strong understanding of Model Evaluation Techniques and the use of tools like SHAP for interpreting machine learning models and ensuring fairness and transparency in model decisions.

Data Scientist at Medgo2u (2024-04 – Present)

• Collaborated with cross-functional teams and non-technical stakeholders to define project objectives, gather requirements, and deliver data-driven solutions that support business goals and improve operational efficiency
• Developed a machine learning–based error detection system for clinical notes using the BioClinical BERT model, enabling near real-time identification of contextual inconsistencies and significantly improving documentation quality
• Built a text summarization model to convert ASR transcripts into structured clinical chart notes using the BART large language model (LLM), improving the efficiency and readability of clinical documentation
• Designed and implemented an AI-based document processing system using OCR and NLP techniques to automatically extract and classify key information from clinical documents, including patient names, provider details, dates of birth, and service dates
• Applied Natural Language Processing techniques such as TF-IDF feature extraction, Named Entity Recognition (NER), and multiclass classification models to improve information extraction accuracy from healthcare records
• Developed and maintained machine learning workflows for model training, evaluation, and deployment, ensuring consistent model performance and efficient integration into operational processes
• Built automated data preprocessing and feature engineering pipelines to clean, transform, and structure large clinical datasets for machine learning model training and analytics
• Designed data pipelines and optimized SQL queries to process and analyze large datasets, reducing data processing time by 50% and enabling faster generation of analytical insights
• Conducted exploratory data analysis (EDA) to identify patterns, anomalies, and data quality issues in clinical datasets, improving model performance and decision-making accuracy
• Developed interactive dashboards and reports to communicate model insights, performance metrics, and key findings to stakeholders and decision-makers
• Built an NLP-based clinical document processing system that improved information extraction accuracy by 35% and reduced manual review time by 40%
• Implemented machine learning models for clinical text error detection, improving documentation quality and reducing inconsistencies in healthcare records
• Optimized SQL queries and data transformation processes, reducing data processing time from 8 hours to 4 hours and improving data availability for analytics teams

Data Specialist at Wipro (2021-11 – 2024-08)

• Designed and implemented feature engineering techniques to improve model performance and increase predictive accuracy across multiple datasets
• Conducted A/B testing and statistical hypothesis testing to evaluate the effectiveness of product improvements and business strategies
• Implemented data preprocessing techniques, including missing value handling, outlier detection, normalization, and categorical encoding, to prepare datasets for machine learning models
• Applied time series forecasting techniques to analyze historical trends and predict future demand patterns
• Collaborated with data engineers and analysts to integrate machine learning outputs into reporting workflows and business dashboards
• Built automated model evaluation pipelines to monitor model performance and ensure reliability over time
• Created visualizations using Python libraries such as Matplotlib and Seaborn to communicate complex analytical insights to stakeholders
• Designed data-driven solutions for customer segmentation and behavioral analysis using clustering algorithms such as K-Means and hierarchical clustering
• Delivered data storytelling presentations that translated technical findings into actionable insights for business leaders and non-technical teams

MSc in Data Science and Analytics – Cardiff University (2024-09 – 2025-09)

B.E in Mechanical Engineering – Nitte Meenakshi Institute of Technology (2017-05 – 2021-08)

Advanced Business Intelligence Programme – IIM