Alejandro Correa Bahnsen, Developer in Bogotá - Bogota, Colombia
Alejandro is available for hire
Hire Alejandro

Alejandro Correa Bahnsen

Verified Expert  in Engineering

Machine Learning Developer

Location
Bogotá - Bogota, Colombia
Toptal Member Since
October 9, 2015

Alejandro holds a PhD in machine learning. He has over 15 years of experience developing data science projects in different areas, including credit card fraud detection, credit scoring, collections, churn, and direct marketing. While working at Rappi, Latam's largest tech unicorn, Alejandro led a team of more than 100 data scientists. He actively contributes to open-source projects such as scikit-learn.

Portfolio

Easy Solutions, Inc.
NoSQL, Big Data, Scikit-learn, R, Python
Rappi
Machine Learning, Python, Amazon Web Services (AWS), Management, APIs
Universidad de los Andes
GPT, Natural Language Processing (NLP)...

Experience

Availability

Part-time

Preferred Environment

Python, Solution Architecture, Apache Airflow, Amazon Web Services (AWS), Google Cloud Platform (GCP), Deep Learning, Chatbots, Recommendation Systems, Data Lakes, Snowflake

The most amazing...

...thing I've helped develop is CostCla, a Python library used for implementing several cost-sensitive machine learning models to solve real-world problems.

Work Experience

Lead Data Scientist

2015 - PRESENT
Easy Solutions, Inc.
  • Managed the data science team.
  • Developed machine learning models for information security.
Technologies: NoSQL, Big Data, Scikit-learn, R, Python

Chief Artificial Intelligence Officer

2019 - 2022
Rappi
  • Utilized machine learning for forecasting candidates' KPIs.
  • Optimized resource allocation and created recommendation engines.
  • Created a different API type to allow the use of machine learning modules.
Technologies: Machine Learning, Python, Amazon Web Services (AWS), Management, APIs

Professor of the Master in Analytics

2016 - 2016
Universidad de los Andes
  • Oversaw courses in natural language processing, big data, and machine learning.
Technologies: GPT, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Data Science, Statistics, Machine Learning

PhD Researcher

2012 - 2015
University of Luxembourg
  • Developed example-dependent cost-sensitive classification techniques.
  • Created a machine learning technique tailor-made for credit card fraud detection.
  • Applied cost-sensitive predictive modeling to a variety of real-world applications such as credit card fraud detection, credit scoring, churn modeling, and direct marketing.
Technologies: SQL, Spark, Scikit-learn, R, Python

Fraud Data Scientist

2012 - 2015
SIX Financial Services
  • Developed intelligent reporting to support the card management team.
  • Implemented advanced cost-sensitive classification credit card fraud detection models.
Technologies: Oracle, SQL, R, Scikit-learn, Python

Data Scientist

2010 - 2012
Scotia Bank/Colpatria Bank
  • Implemented genetic algorithm and particle swarm optimization models in SAS for selecting the best architecture of a multi-layer perceptron neural network, and for selecting the variables that maximize the KS statistic in a logistic regression model.
  • Created different cluster analyses for the risk and marketing areas, for clients segmentation and model segmentation, among others.
Technologies: SQL, PHP, MATLAB, Visual Basic for Applications (VBA), R, SAS

Statistical Models Analyst

2008 - 2010
GE Money/Colpatria Bank
  • Developed acquisition and behavior scorecards for calculating clients' probability of default, using logistic regression, CHAID decision trees for variables binning, binary genetic algorithm optimization for variable selection, and multi-layer perceptron neural networks.
  • Created a constraint optimization algorithm for assigning collection treatments to bank clients, using the probability of a client of falling in next bucket as an input, the expected response per client per treatment, total balance, and treatments costs.
Technologies: MATLAB, PHP, Visual Basic for Applications (VBA), SQL, R, SPSS, SAS

Six Sigma Intern

2006 - 2008
The Dow Chemical Company
  • Developed reports for the commercial and marketing areas.
  • Created GARCH and ARIMAX models for forecasting raw materials prices.
  • Responsible for a Six Sigma project for time cycle reduction on international orders. The result was the building of a new warehouse on a Colombian free trade zone.
  • Developed several marketing research projects for plastics, construction, and chemical departments.
Technologies: SAS, Visual Basic for Applications (VBA), Oracle

Tutorial EDCS Credit Scoring

An IPython Notebook (now Jupyter) about a tutorial of CostCla, a cost-sensitive classification library in Python. Some requirements to run it include Python 2.7 and a pip install of Numpy, Scikit-learn, Pandas, PyEA, and CostCla.

CostCla Python Library

https://github.com/albahnsen/CostSensitiveClassification
CostCla is a Python module for cost-sensitive machine learning (classification) built on top of Scikit-Learn and SciPy and distributed under the 3-Clause BSD license.

In particular, it provides a set of example-dependent cost-sensitive algorithms and different real-world example-dependent cost-sensitive datasets.

Contributor Sklearn

http://scikit-learn.org/
Contributor to the scikit-learn project.

Languages

SAS, Python, SQL, R, Visual Basic for Applications (VBA), PHP, C++, C, Snowflake

Libraries/APIs

Scikit-learn, NumPy, SciPy, Flask-RESTful, Node.js, Pandas

Tools

IPython Notebook, Microsoft Excel, MATLAB, PyCharm, Jupyter, SPSS, Apache Airflow, IPython

Paradigms

Data Science, REST, Management

Platforms

Azure, Amazon Web Services (AWS), Oracle, Ubuntu, RStudio, Linux Mint, Google Cloud Platform (GCP), Jupyter Notebook

Other

Data Structures, Algorithms, Big Data, Applied Mathematics, Machine Learning, Natural Language Processing (NLP), Deep Learning, Statistics, Data Mining, Optimization Algorithms, Data Analysis, GPT, Generative Pre-trained Transformers (GPT), Solution Architecture, Chatbots, Recommendation Systems, APIs

Frameworks

Flask, Hadoop, Apache Spark, Spark, Django

Storage

MongoDB, PostgreSQL, NoSQL, MySQL, Data Lakes

2012 - 2015

Ph.D. Degree in Machine Learning

Luxembourg University - Luxembourg

2008 - 2010

Master's Degree in Operations Research, Finance, and Statistics

Universidad de los Andes - Bogota, Colombia

2002 - 2008

Bachelor Degree in Industrial Engineering

Universidad de los Andes - Bogota, Colombia

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring