My Projects

Data Science & Machine Learning Solutions

Pricing Optimization

MIT Collaboration: Furniture Pricing Optimization

Cutting-edge pricing optimization project in collaboration with MIT, targeting profitability improvements of 5-20% through strategic implementation of machine learning algorithms and web application deployment.

5-20% Profitability Increase
National Scale Deployment
NumPy Pandas Scikit-Learn IBM Cloud Pack IBM CPLEX SQL

Key Features: Web application deployment, time series analysis, forecasting models, optimization algorithms

Deep Learning

Advanced Clothing Pricing with Neural Networks

Developed cutting-edge pricing models using Feedforward Neural Networks (FNN) and LSTM networks, incorporating Time Series Clustering for demand analysis across national clothing markets.

Neural Network Innovation
Time Series Clustering
Keras TensorFlow Azure Data Studio SQL Server Matplotlib Seaborn

Key Features: LSTM networks, demand forecasting, unsupervised clustering, short-term forecasting

Predictive Analytics

Motorcycle Agency Expansion Prediction

Spearheaded predictive modeling initiative to guide expansion strategy targeting 542 localities by 2030. Built and validated machine learning models using 117-119 locality-level variables from multiple data sources.

542 Locations Analyzed
2030 Strategic Planning
Python Scikit-learn XGBoost SQL INEGI Data Geo Data

Key Features: Feature engineering, external data integration, ranking algorithms, sales prediction models

Computer Vision

CV-Driven Process Automation

Led conceptualization and execution of Computer Vision automation system using transfer learning with MobileNet network, integrated into API for bot automation.

Process Automation
API Integration
TensorFlow PyTorch OpenCV MobileNet SCRUM

Key Features: Transfer learning, image classification, automated workflows, API development

Computer Vision

Facial Expression Recognition for Retail

Developed FER model for in-store customer analysis using transfer learning with Xception and Inception architectures to understand customer reactions and emotions.

Customer Analysis
Emotion Recognition
TensorFlow PyTorch OpenCV Xception Inception Google Colab

Key Features: Transfer learning, emotion classification, retail analytics, real-time processing

Cloud Vision

Visual Search on Google Cloud Platform

Led team of 4 in creating visual search demo leveraging Google Cloud Platform with object detection and semantic segmentation capabilities.

Team Leadership
Cloud Deployment
GCP Docker TensorFlow PyTorch Flask Git Linux

Key Features: Object detection, semantic segmentation, cloud repositories, scalable deployment

NLP

Federal Justice Text Classification

Led development of sophisticated NLP model for "National Census of Federal Justice Impartation" to pre-classify federal offenses using natural language processing techniques.

National Census
Legal AI
NLP Machine Learning Text Classification Feature Engineering Microsoft SQL Server

Key Features: Legal text analysis, offense classification, feature engineering, automated processing

Statistical ML

Time Series Clustering for Judicial Statistics

Implemented innovative unsupervised clustering algorithm for strategic human resource allocation based on time-series patterns in judicial data.

Resource Optimization
Statistical Innovation
SPSS R Hierarchical Clustering Time Series Analysis Microsoft Office

Key Features: Unsupervised learning, hierarchical clustering, pattern recognition, resource allocation

Operations Research

National Queue Management System

Enhanced queue management for retail stores nationwide using clustering algorithms and queueing theory to optimize customer flow dynamics and create performance KPIs.

National Scale
Customer Flow Optimization
NumPy Pandas Scikit-Learn Queueing Theory Jupyter Notebook DBeaver

Key Features: Store clustering, KPI development, queueing optimization, national implementation

Recommendation Systems

Pagerank-Based Personalized Recommendations

Developed algorithm delivering personalized recommendations using Pagerank principles with multiprocessing for scalable execution and rapid response times.

Personalization
Scalable Architecture
PySpark Pagerank Algorithm Multiprocessing Big Data

Key Features: Graph algorithms, parallel processing, personalization engine, big data handling

Educational Software

Apolonio v1: Mathematical Visualization Tool

Developed graphical interface for teaching generalizations of geometric curves (circle, ellipse, parabola, hyperbola) for the Laboratory of Scientific Computation at UNAM.

Educational Innovation
UNAM Research
Matlab Mathematical Visualization GUI Development Educational Technology

Duration: JAN 2007 - DEC 2010

Key Features: Interactive visualization, mathematical education, curve generation, academic research tool