Enthusiastic of engineering and science. Analytic, autodidactic, and responsible. Always learning something new. Looking for the best solutions.
Designing engineering solutions and trying to contribute to machine learning state-of-art.
2019
Application of machine learning techniques and models for sentiment analysis. Design of web services.
2018 - 2019
Analysis, design and development of a dollar account management system.
2014 - 2016
Analysis, design and development of an information orchestrator for financial system. Database managment.
+52 5565117721
urielcoro@gmail.com
urielcoro@outlook.com
Analysis, design and development of an information orchestrator for financial system. Customized ETL components development. Analysis, design and development of the back-end for scheduled database queries. Analysis, design and development of a database objects management.
Java EJB Pentaho Quartz SQL HTML5 Bootstrap JQuery
Analysis, design and development of a dollar account management system: Requirements gathering, database analysis and design, front-end design, back-end development, unitary tests, integration tests and final-user tests. Code integration using CI/CD pipelines.
Spring boot Spring batch SQL Server Jenkins SVN
We wrote a paper where we present a deep reinforcement learning-based
methodology for computing optimized trading policies. During the first
stage of the methodology, we employ Gated Recurrent Units (GRUs)
to predict the immediate future behaviour of the time series that de-
scribe the temporal dynamics of the value of a set of assets. Then, we
employ a Deep Q-Learning Architecture to compute optimized trading
policies that describe, at every point in time, which assets have to be
bought and which have to be sold in order to maximize profit. Our ex-
perimental results, which are based on trading cryptocurrencies, show
that the proposed algorithm effectively computes trading policies that
achieve incremental profits from an initial budget.
Here you can find the reference to the article.
PyTorch Git
Transfering style in text among multiple classic authors using Generative Adversarial Networks. The first task was to generate shared encodings for all authors and decode them for each author separately. The team left the project since it is difficult to automatically measure the similarity in texts styles. Here you can find our advances.
PyTorch Git
Investigation, modification, training and evaluation of machine learning models applied to natural language processing. CI/CD pipelines configuration. Development of the first version front-end of a metrics board. Analysis, design and development of a IA-based metrics system. Design of a system architecture. Code integration.
PyTorch Tensorflow Azure DevOps Vue HTML5 Bootstrap MongoDB PostgreSQL Node4j Flask Docker Git
