Mercado Libre

Audience project: 
- Business problem framing: Uplift modeling, RFM, Open Push Modeling 
- Analytics problem framing: binary classification

Remarketing project:
- Build and deploy Uplift model with trees based models and A/B testing it.
- Exploratory Data Analysis

Mendel project:
- Build data architecture to bind heuristics, models and audience. 
- Exploratory Data Analysis.

Senior Data Scientist

Pontificia Universidad Javeriana

Docente curso: Tópicos Avanzados en Analítica, Maestría Analítica para la Inteligencia de Negocios.

Docente catedrático

Politécnico Grancolombiano

Build Analytics Solutions (descriptive, predictive, prescriptive).

Implement:
• MaaS (Model as a Service)
• AIaaS (AI as a Service)
• NaaS (Notebook as a Service)

Director Advanced Analytics & BI

• Machine Learning Systems: Dashboards (Streamlit, Shiny, Dash), Rest APIs (Flask).

• ML/DL: Ensemble Methods, Linear Models, RNN, CNN, Transfer Learning (NLP).

• Technologies and languages handled: Linux, AWS, Git, Heroku, Python (PuLP, Pyomo, Flask, Dash, Plotly, Tensorflow, Sklearn, Scipy, Pandas...), R (Parallel, caret, MASS, Shiny, Tidyverse, ...), SQL (MySQL, PL/SQL), OLAP Cube.

Analytics and Data leader - Lead Data Scientist

Machine Learning:
 • Aprendizaje Supervisado, clasificación (k-Nearest Neighbors, Naive Bayes, Logistic Regression, Multi-label and Multi-class problems)
 • Aprendizaje Supervisado, regresión (Linear Regression, Non-linear responses, Ensembles Methods: Boosting, Bagging and Stacking)
 • Aprendizaje No Supervisado (K-means Cluster, Dimensionality reduction with PCA and t-SNE)

Data Warehouse:
 • Data Quality (ImportData, Clean Data, Data Manipulation, Joining Data).
 • Cubing Services (Multidimensional and tabular models, solution planning in BI). 
 • ETL in SSIS.


Big Data:
 • Procesar a código eficiente (Code Profiling, Parallel Programming)
 • Construir estrategias para visualizar Big Data (ggplot2 + TrelliscopeJS, Trelliscope in the Tidyverse)
 • Scalable Data Processing (Processing and Analyzing Data with bigmemory)
 • Spark (Sparkr, Pyspark, Running Machine Learning Models on Spark).

Project Management:
 • Mejorar la productividad, eficacia de los recursos y la consecución de objetivos bajo el uso de herramientas computacionales y modelos matemáticos tecnológicos.
 • Tomar decisiones, supervisar equipos, tareas y proporcionar soluciones de analítica.
 • Construcción de proyectos de analítica para sostener y apoyar la transformación digital en instituciones de educación superior.

Data leader

Data Warehouse:
   • Data Quality (ImportData, Clean Data, Data Manipulation, Joining Data).
   • Cubing Services (Multidimensional and tabular models, solution planning in BI). 

Machine Learning:
  • Aprendizaje Supervisado, clasificación (k-Nearest Neighbors, Naive Bayes, Logistic Regression, Classification Trees)
  • Aprendizaje Supervisado, regresión (Linear Regression, Non-linear responses, Tree-Based Methods)
  • Aprendizaje No Supervisado (K-means Cluster, Hierarchical clustering, Dimensionality reduction with PCA)

Data - Data Scientist

Processes carried out in the Academic Information System (BANNER):
• Program management
• Curriculum rules
• CAPP
• Catalog of courses
• Administration of agreements for homologation and articulation

Proposed processes for Academic Development:
1. Perform exploratory data analysis (Approved and in building)
2. Implement correlations and regressions (Approved and under construction)
3. Build Cluster Analysis (Proposed)
4. Implement supervised learning models to classify data (Proposed)
5. Implement unsupervised learning models (Proposed)
6. Creation of Neural Networks (Proposed)
7. Build a model of Support Vector Machines (Proposed)

Process Analyst

• Administrator and collaborator in the creation of the curricular mesh model.
• Parameterization of programs in Information Systems.
• Control and assurance of academic curricula.
• Support in audits in front of the National Accreditation Council (CNA) and Quality Assurance Service in Higher Education (SACES).
• Support in renewing qualified records, creations of qualified records and academic accreditation.
• Qualitative analysis of syllables.
• Administrator of the syllabus catalog of subjects and virtual modules.
• Comparison of Institutional Prerequisites.
• Projection and consideration of programs.
• Financial Forecast based on curricula and subjects.
• Consolidation in the Department of Assurance of the Institutional Agreements.
• Control and assurance of systems with parameters in the system.
• Collaboration in indicators for the program for the renewal of the qualified registry.

Monitor of Quality Assurance and Strategic Planning.

FENADECO Colombia

•	Promover las actividades realice FENADECO Nacionalmente. 
•	promover suscripción de convenios, mantener y establecer nuevos canales de comunicación entre FENADECO y las universidades a nivel nacional.
•	participar en la realización de eventos Académicos de los Capítulos Universitarios, Comités Locales de Trabajo, Asambleas Regionales o Asambleas Nacionales del año en curso.
•	velar por el optima comunicación y representación de los estudiantes dentro las universidades pertenecientes a la Federación..
•	Así mismo, funciones que de su naturaleza deba ejercer o que le sean asignados por el Comité Coordinador Nacional o la Asamblea Nacional de Delegados.

National Director of Academic Affairs

Bancolombia

Was an administrative officer with emphasis in Human Resources, giving the possibility of innovating in the experience of the labor field, tabulation, reception of documents, sending of tests, communication with senior managers, programming of interviews, and functions in The same margin to the area played. This learning contract does not impede the development of university internships. 

Link of interest: http://www.accounter.co/normatividad/conceptos/diferencia-entre-contrato-de-learning-and-the-pasantias-que-cumplen-estudiantes-al-culminar-sus-estudios-profesionales. Html

Learning contract (SENA)

github: https://sergiomora03.github.io/ Economista del Politécnico Grancolombiano y candidato a magister en la Universidad de los Andes. Ha sido ponente en temas de modelación estocástico en mercados financieros y modelos de lógica difusa en congresos internacionales tales como el Congreso Iberoamericano en Economía Aplicada. Es coautor de uno de los capítulos del libro MODELING AND SIMULATION IN MANAGAMENT SCIENCE, editorial SPRINGER, titulado "Light Innovation in Energy Supply for Non-connected Areas in Colombia: Partial Research via the Forgotten Effects Model". Sus intereses se centran en investigación cuantitativa, Econometría, Análisis Predictivo, Series de Tiempo, combinando técnicas y algoritmos de Aprendizaje Autómatico (Machine Learning) y Aprendizaje Profundo (Deep Learning).

Taplio

Sergio Mora Pardo's Linkedin Analytics

Sergio Mora Pardo

Want to drive more opportunities from LinkedIn?

Taplio

.css-1jgreyo{background-image:linear-gradient(284deg, rgba(39,43,72,1) 0%, rgba(33,47,183,1) 100%);color:transparent;-webkit-background-clip:text;background-clip:text;}Sergio Mora Pardo's Linkedin Analytics

Sergio Mora Pardo

Want to drive more opportunities from LinkedIn?

Sergio Mora Pardo's Linkedin Analytics