- Machine Learning: Supervised/unsupervised models, hyperparameter tuning, GridSearchCV, SVM, GradientBoosting.
- Deep Learning: Neural networks with TensorFlow, PyTorch.
- Data Science: Data analysis, feature engineering, data pipelines with Python (Pandas, NumPy, Scikit-learn).
- Deployment: ML models in production using Flask, Docker, APIs.
- Languages: Python, R, C++, MATLAB, SQL.
-
Credit Risk Models Developer: Led the successful implementation of predictive models for credit risk evaluation, including incurred and expected loss models, improving the companyβs ability to manage and forecast financial risk.
-
Real-time Noise Measurement Algorithm Developer: Designed and implemented a real-time algorithm for noise level measurement, utilizing IoT technology, and achieving Class 1 sound level meter certification.
-
Web Scraping and Data Analysis Lead: Developed advanced scraping algorithms and utilized graph-based data visualization to enhance marketing decision-making and data completeness.
- Spark-NLP-Bank-Complaints-Classification: This repository focuses on classifying customer complaints related to various banking products using Spark NLP. It includes natural language processing techniques, classification models, and advanced hyperparameter optimization.
- Happiness Prediction: Predicting happiness using classification models and advanced hyperparameter optimization.
- GraphInsight: GraphInsight is a recommendation system that uses a bipartite graph to link users and products based on their interactions. By calculating user similarities, it recommends products using Python libraries like Pandas and NetworkX, leveraging a synthetic dataset for experimentation.
GitHub Stats | Top Languages |
---|---|
- Platzi Profile: Sebastian Carvalho