👋 Hello! This is ishak passionate about leveraging data to unravel insights and make informed decisions. With a strong foundation in data visualization, statistical analysis, and machine learning, I'm dedicated to exploring datasets to extract valuable insights and drive data-informed solutions. @Issaakee
Developed a robust consent verification system using AWS Lambda, API Gateway, and Amplify, integrating Whisper Tiny and ML algorithms to transcribe audio, analyze user consent, and ensure accurate compliance checks.
Built a scalable speaker diarization pipeline leveraging AWS Lambda, SQS, and S3, incorporating PyAnnote models to detect, segment, and analyze speakers in audio files, significantly enhancing audio processing workflows for production use.
I developed an end-to-end machine-learning pipeline for this project using a publicly available car dataset from Kaggle. The pipeline covered data collection, preprocessing, exploration, feature engineering, model training, and assessment and concluded with insights drawn from the analysis.
I developed a model to classify ASL hand signs using the Sign Language MNIST dataset. The process included data loading, preprocessing, augmentation, and exploration. Various models and hyperparameter configurations were experimented with, and the performance was evaluated using confusion matrices and training history plots.
In this task, I developed an NLP system to identify emotions in Twitter posts using the "Emotions" dataset from Kaggle. The process included preprocessing the dataset, and cleaning the text data. Various models were compared and hyperparameters tuned. The results were evaluated using accuracy plots, confusion matrices, and word clouds, leading to a final discussion of the system's performance.
Performed a comprehensive exploratory data analysis on the Paris 2024 Olympic Games, analyzing athlete performance, event schedules, and key patterns. Created detailed visualizations and extracted actionable insights using Python libraries such as Pandas, Matplotlib, and Seaborn.
For this project, I conducted exploratory data analysis (EDA) on a publicly available dataset from Kaggle. Given my deep interest in football, I analyzed the dataset, covering necessary steps, including business context, data exploration, preprocessing, and a thorough EDA, followed by a discussion on the strengths and limitations of the analysis.
