Muhammad Nisar

• Created an XGBoost model to predict Type 2 Diabetes using metabolite profiles, enhancing accuracy by 27% over baseline models through rigorous data cleaning, feature engineering, and iterative model training.
• Designed and built scalable data pipelines for head and neck cancer research, leveraging NLP techniques to analyze extensive datasets and construct a specialized database, resulting in a 40% reduction in data processing time through advanced data engineering and optimization strategies.
• Partnered with cross-functional teams to integrate machine learning models into data-driven decision-making processes, achieving a 50% reduction in processing time and boosting research eficiency through advanced analytics and algorithm optimization.
• Engineered and refined an NLP-based chatbot for interactive communication, applying vectorization techniques and semantic analysis to boost user engagement by 25% through enhanced natural language understanding and machine learning methods.

• Developed and optimized an insurance cost prediction model using various machine learning algorithms, achieving a 15% improvement in prediction accuracy compared to legacy models through advanced model tuning and hyperparameter optimization.
• Conducted thorough accuracy assessments and model validation, utilizing cross-validation and performance metrics (such as accuracy, F1-score, precision, and recall), improving the models accuracy by 10-15%, contributing to a noticeable increase in stakeholder confidence and supporting more reliable decision-making for business operations.
• Acquired comprehensive expertise in machine learning techniques, including model selection, training, and evaluation, enhancing overall project eficiency and efectiveness.