Bio: 👋 I'm am a Data Engineer & Data Science with Software Eng skills. With expertise in ETL, ML, & app development. I specialize on end-to-end solutions.
I am a passionate and dedicated machine learning engineer with a proven track record of developing high-scale machine learning workflows. Leveraging a robust blend of data science, data engineering, and software engineering skills, I specialize in creating innovative solutions to complex problems. My expertise spans various machine learning techniques, including linear regression, classification, clustering, and Natural Language Processing (NLP) tasks. I have extensive experience designing and implementing predictive models that drive actionable insights and business value. Whether it is building sophisticated ETL and Reverse ETL pipelines or optimizing models for predictive accuracy, I thrive on tackling challenging projects and delivering exceptional results.
In addition to my technical skills, I am committed to continuous learning and staying abreast of the latest advancements in the field. I advocate for best practices in machine learning and software development practices, ensuring that my workflows are efficient, scalable, and maintainable. I enjoy collaborating with cross-functional teams to translate business requirements into technical specifications, and I am adept at communicating complex technical concepts to non-technical stakeholders. My goal is to harness the power of machine learning to solve real-world problems and contribute to impactful projects.
Followed the CRISP-DM process to clean, transform, and evaluate two algorithms (multiple linear regression and random forest regression) to predict AIRBNB listing prices
CVSARIMAX is a Python package designed to facilitate robust forecasting by implementing sequential cross-validation techniques with SARIMAX models. This package provides an essential tool for analysts and data scientists who need to evaluate time series forecasting models accurately, ensuring that the temporal integrity of the data is maintained.
Created a web app to display disaster response categories predicted based on a random forest classifier trained over an NLP pipeline that cleans, stems, lemmatize, and vectorize the provided data
Applied unsupervised learning techniques to identify segments of the population that form the core customer base for a real-life mail-order sales company in Germany to aid the direct marketing campaigns towards audiences that will have the highest expected rate of returns.
Employed several supervised algorithms and chose the best candidate algorithm from preliminary results using data collected from the 1994 U.S. Census and further optimize this algorithm to best model the data to accurately predict whether an individual makes more than $50,000.
Predict when users are about to churn or cancel the services. So basically it is a warning detection to prevent possible revenue loss due to service cancelling. It uses a Random Forest Classifier to as the model of choice.
This is where I refine my skills by constantly taking Udemy courses. I push the contents of the course here, including my practice files, to be able to clone them from wherever I am. I also practice git this way.