classMiguelRocha:def__init__(self):self.role="Solutions Architect @ Google"self.location="Seattle, WA"self.work_experience=6self.education= {"masters":"M.S. Business Analytics (UT Dallas)","bachelors":"B.S. Information Technology (UT Dallas)"        }self.interests= ["Generative AI","Machine Learning","Cloud Architecture"]defcurrent_focus(self):return ["Large Language Models (LLMs)","RAG Implementations","Multimodal AI Solutions","Enterprise Cloud Architecture"        ]

• 🎯 Led development of credit risk models saving several $MM for clients
• 🚀 Successfully deployed ML models on various cloud platforms
• 📊 Developed decision engines resulting in $28MM annual savings

• Coming Soon...

Python        12 hrs 40 mins  ███████████░░░░░░  45.2%ML/AI Tasks    8 hrs 15 mins  ██████░░░░░░░░░░░  29.4%Cloud Dev      4 hrs 30 mins  ████░░░░░░░░░░░░░  16.1%Documentation  2 hrs 35 mins  ██░░░░░░░░░░░░░░░   9.3%

# Life Philosophywhilealive:learn()code()innovate()repeat()

PinnedLoading

1. Employee-AttritionEmployee-AttritionPublic

   Identifying whether an employee will leave the company based on an employee's attributes. I used ML algorithms such as Random Forest, Logistic Regression, Naive Bayes, and LightGBM

   Jupyter Notebook

2. Kaggle-Nomad2018Kaggle-Nomad2018Public

   I placed top 16% in the world on Kaggle in this competition. I used keras and tensorflow for deep learning and several ensembles with least correlated estimates to optimize for accuracy.

   Jupyter Notebook 1

3. Predicting-Breast-CancerPredicting-Breast-CancerPublic

   Given a breast tumor's attributes, I used several machine learning models to predict whether if the tumor is malignant or benign

   Jupyter Notebook

4. House-PricesHouse-PricesPublic

   I used Random Forest to predict a house prices given the house's attributes

   Jupyter Notebook