Developed an AI-powered platform leveraging LLMs and reinforcement learning to intelligently assign tasks and adapt based on employee allocation outcomes, ensuring balanced workloads across all resources

• Conducted research under the mentorship of Professor Muhammad Ahmad, on the evaluation and quantification of fairness metrics in machine learning models applied to healthcare datasets• Built and optimized ML models using Logistic Regression, k-Nearest Neighbors, and Gradient Boosting algorithms to analyze the disparate impacts of treatment predictions based on attributes such as age, race, and gender• Improved ML model accuracy by 20%Skills: Python • Gradient Boosting Algorithms • Regression • k-Nearest Neighbors • Machine Learning • AI Ethics

• Developed Python code to train ML models to analyze biases in the juvenile justice system. Discovered high levels of racial bias in existing systems• Fine-tuned the hyper-parameters of Logistic Regression and Random Forest algorithms to enhance performance• Improved accuracy of the ML models by 15-20%Skills: Data Analytics • Artificial Intelligence • Logistic Regression • Random Forest • NumPy • Pandas

Built and trained machine learning models using algorithms such as Naive Bayes, Neural Networks, and Random Forest to detect bias crimes in police reportsSkills: Data Visualization, Exploration, and Bias • Supervised & Unsupervised Machine Learning • NLP • Classifiers

• Worked in a team to develop an end-to-end ECG-based heartbeat biometric system for secure authentication, focusing on signal processing and feature extraction techniques• Applied ML models such as Support Vector Machines in R to analyze heartbeat variability and enhance accuracy in biometric identificationSkills: R Studio • Support Vector Machines • Image Processing • Statistical Analysis • Matlab