
Manuel Montoya Catala
Verified Expert in Engineering
Deep Learning Developer
Manuel is an enthusiastic senior data scientist with 3+ years of experience in consulting and a background in machine learning research. After several years of both business and academic experience, he acquired knowledge in diverse areas ranging from statistical analysis to deep learning. He is a results-oriented person with excellent communication skills. Manuel works with dynamic teams in the standard setup consisting of Python, AWS or Azure, Agile, Git, and Visual Studio.
Portfolio
Experience
Availability
Preferred Environment
Visual Studio, PyCharm, Deep Learning, Data Science, Machine Learning, Git, Amazon Web Services (AWS), Agile Practices, Python, Azure, Statistical Modeling
The most amazing...
...thing I've developed is an automatic trading platform in Python and a Bayesian deep learning architecture to solve the Q&A task in PyTorch.
Work Experience
Senior Data Scientist
Damvad
- Developed an end-to-end data analysis pipeline for yield optimization and predictive maintenance in a large enzyme producer company. This generated an increase in yield of 5–10%.
- Designed and developed a churn prediction system for a big hearing aid company, resulting in the early detection of 70% of the returned devices.
- Designed and developed a realistic patient data generation system for a healthcare company, resulting in hundreds of hours saved of manual work per clinical trial and reducing waiting time by 2–4 weeks.
Teaching Assistant at Multivariate Statistics
Danish Technical University
- Created the materials for exercise sessions of the course.
- Solved the exercises in class together with the students.
- Developed the SAS code examples of the course and the baseline analysis of the data.
Full-stack Developer
Danske Bank
- Developed financial analysis tools for private banking clients.
- Created dashboards for enhanced decision-making in portfolio management.
- Developed automatic report generation systems with OpenXML.
- Designed and implemented SQL databases to integrate the different sources of financial data.
- Performed portfolio analysis based on allocations across currency, sectors, countries, and types of financial assets.
Researcher and Teaching Assistant
University Madrid Carlos III of Madrid
- Served as a teaching assistant for the master-level course on data processing.
- Wrote a publication called "Experiments in combining boosting and deep stacked networks."
- Developed a Python library for the deep architecture called B-ADSN.
- Created the materials (code and presentations) for the courses Signals and Systems and Electromagnetic Fields.
Experience
Factory Optimization Web App for a Big Enzyme Producer
Trapyng | Trading in Python
The platform focuses on the proper visualization of the strategies and the understanding of the underlying methods, promoting the generation of new ideas for future trading strategies.
I started this project in 2016 with the goal of properly applying machine learning in trading. I took professional trading courses and opened a trading account with a broker to learn how retail traders think and use those insights in the system and data modeling phase.
A few manuals have been created describing the features of the system, although a large number of them are still undocumented due to lack of time. These include advanced linear models, Kalman filters, Gaussian processes, and RNNs, among others.
B-ADSNs: Research at UC3M
This project describes the B-ADSN architecture developed during my research at UC3M. The main results of this research can be found in the referenced IEEE Xplore Publication and all other materials including codes can be found in the linked repository.
The code was entirely developed from scratch in Python without TensorFlow or any other automatic differentiation library since they were not as popular at the time of development in 2015.
Directional Statistics Tool
The tool was created from scratch in Python and It contains many functionalities such as being able to combine clusters from different distributions, it can recover from degenerate clusters and it is very customizable.
The code of the final tool can be found in the referenced repository and along with its documentation. In the repository, you can also find example videos that can be generated by the tool and its applications to EEG data.
Potential Sea-Wave Energy Prediction (2014)
Neural networks are used in order to predict such height, the input data is a combination of historical weather conditions and sea-waves parameters from other areas of the ocean worldwide. Meta-heuristic search techniques are used to find the subset of these parameters that produces the best prediction.
The project is completely implemented in C from scratch using the CBLAS library and POSIX threads for optimizing the speed.
The main focus of the project is the feature selection of the variables, which is done by combining a fast regression algorithm, the extreme learning machine, and discrete optimization local search heuristics such as simulated annealing and evolutionary algorithms.
Bayesian BiDAF-ELMo System in PyTorch
https://github.com/manuwhs/BiDAF-ELMo_BayesianThe architecture incorporates multiple deep learning models, including bi-directional LSTMs, highways, and attention mechanisms. Additionally, I have extended these architectures with a Bayesian approach, which can be accessed in the repository.
Skills
Languages
Python, SQL, SAS, R, C, C++
Paradigms
Data Science, Agile, ETL
Platforms
Jupyter Notebook, Amazon Web Services (AWS), Azure, Docker
Other
Machine Learning, Data Analysis, Data Analytics, Statistical Modeling, Artificial Intelligence (AI), Linear Regression, Predictive Modeling, Statistics, Time Series Analysis, Data Visualization, Deep Learning, Dash, Data Engineering, Clustering, Natural Language Processing (NLP), CI/CD Pipelines, Azure Data Factory, Azure Databricks, Serverless, Hugging Face, MLflow, Scrum Master, Business Proposals, DeepSNAP, PyTorch Geometric (PyG), GNN, Graphical Models, BERT, Real-time Data, Convolutional Neural Networks, Machine Learning Operations (MLOps), Dashboards, Quantitative Finance, Quantitative Modeling, Quantitative Analysis, GPT, Generative Pre-trained Transformers (GPT)
Libraries/APIs
Pandas, NumPy, XGBoost, Natural Language Toolkit (NLTK), Shapely, Scikit-learn, NetworkX, PySpark, PyTorch, TensorFlow
Tools
Visual Studio, PyCharm, Jupyter, Pytest, Git, Amazon SageMaker, Azure Machine Learning, Plotly, Tableau, Microsoft Power BI
Frameworks
Spark
Storage
NoSQL, Redis
Education
Master's Degree in Mathematical Modeling and Computation
Danish Technical University - Copenhagen, Denmark
Master's Degree in Data Science and Communications
University Madrid Carlos III - Madrid, Spain
Bachelor's Degree in Telecommunications' Engineering
University of Alcalá - Madrid, Spain
Certifications
Machine Learning with Graphs
Stanford University
AWS Certified Cloud Practitioner
Amazon Web Services