Data scientist2018 - 2018Self-employed
- Implemented a reinforcement learning framework for algorithmic trading of cryptocurrencies.
- Worked with Keras in Python.
- Tested several neural network architectures for making trading decisions.
- Tested the framework on artificial time series data.
- Read much of the state-of-the-art literature on reinforcement learning.
Lead Scientist - Text Analysis2012 - 2018Ontotext Ad
Technologies: R, Java, RDF, Ontologies
- Developed machine learning models for NLP, including methods for domain adaptation, methods for automated feature selection, methods for optimization of F-measure. Applied models such as logistic regression, SVM, CRF, for both classification and sequence tagging.
- Developed a machine learning model for classification of tweets as either Rumor/Not Rumor in R.
- Acquired in-depth knowledge in relational databases, ontologies, linked data. Implemented a classification model written in Java, that automatically categorizes Wikipedia pages as either belonging to the topic "Food and Drink" or not.
- Experimented with topic models with LDA in order to help with a reccommender system for a large publishing company.
- Built prototypes for training word-vectors embeddings and graph embeddings.
- Developed models for sentiment analysis for English and Bulgarian, in R and Java. The methods were supervised for English and unsupervised for Bulgarian.
- Acquired significant experience with automated and semi-automated integration of various RDF resources, eg. DBpedia and Geonames.
PhD2006 - 2012Max-Planck Institute für Informatik
Technologies: R, Python
- Gained expertise in Cancer Genetics, with focus on Copy Number Aberrations and acquired additional in-depth knowledge in domains like epigenetics, transcriptomics, viral genomes.
- Used supervised and unsupervised machine learning methods for modeling cancer genetic data. The supervised methods used were: logistic regression, elastic net, SVM, decision trees, random forest. The clustering methods used were: K-means, K-medoids, hierarchical, PAM.
- Wrote Machine Learning models in the statistical language R and acquired in-depth expertise with visualization techniques in R.
- Acquired solid experience with presenting complex AI models to non-experts (medical doctors), by giving the intuition behind the mathematical models.
- Performed feature selection with various methods: filters with statistical tests, penalty methods for linear models, pruning.
- Acquired solid knowledge in computational statistics and statistical learning. This includes statistical tests, statistical distributions, estimators, bias-variance decomposition.
- Wrote scientific papers learned how to deliver high-quality presentations, in conferences or in front of clients.