Degrees

PhD

2018 - 2022. University of Ghent

Thesis: “Studies on advanced natural language processing representations and deep learning in decision making systems”.

Data Analytics team. Educational data mining and natural language processing in a range of applications. A teaching assistant for the course “Data Mining” and Bayesian Statistics. Supervisor: Prof Dr Dries Benoit. Participated in Deep Bayes summer school on deep learning and Bayesian methods; also workshops on public speaking for research and online conferences such as LAK 2021. Collaborated with multiple industry partners and academics from other countries; prepared grant proposals (FWO, BOF).

  • Loginova, Ekaterina, and Dries Benoit. “Embedding Navigation Patterns for Student Performance Prediction.” Proceedings of The 14th International Conference on Educational Data Mining (EDM 2021), edited by I-Han Hsiao et al., Educational Data Mining Society, 2021, pp. 391–99.
  • Loginova, Ekaterina, et al. “Towards the Application of Calibrated Transformers to the Unsupervised Estimation of Question Difficulty from Text.” Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), edited by Ruslan Mitkov and Galia Angelova, INCOMA, 2021, pp. 846–55.
  • Loginova, Ekaterina, et al. “Forecasting Directional Bitcoin Price Returns Using Aspect-Based Sentiment Analysis on Online Text Data.” MACHINE LEARNING, 2021, doi:10.1007/s10994-021-06095-3.
  • Akimov, Mikhail, Ekaterina Loginova, and Maxim Musin. A Graph-Based Approach for Learner-Tailored Teaching of Korean Grammar Constructions. 2018 IEEE International Conference on Data Mining Workshops (ICDMW). IEEE, 2018.

Advanced MSc in Artificial Intelligence

2016 - 2017. KU Leuven

Cum laude. Speech and Language Technology option.

Courses: Machine Learning (19/20), Natural Language Processing, Text Based Information Retreieval, Support Vector Machines, Artificial Neural Networks, Language Engineering Applications, Speech Recognition, Prolog.

Thesis: Sentiment Analysis of news (machine learning). Promotor: Prof Dr Marie-Francine Moens.

BSc in Applied Mathematics and Information Science

2011 - 2015. National Research University Higher School of Economics

Average grade: 8/10. Ranked 10th out of 58 students.

Courses: Algorithms and Data Structures, Data Analysis, Database Theory, Semantic Web, Automatic Text Processing, Statistical Simulation and Analysis, Predictive Modeling, Applied Graph Theory, Theory of Decision Making, Probability Theory and Mathematical Statistics, Calculus, Linear Algebra, Numerical Methods, Game Theory.

Thesis: Information Extraction from news (rule-based). Supervisor: Prof Dr Elena I. Bolshakova

Certificates

DeepLearning.AI TensorFlow Developer

2021. DeepLearning.AI. Grade: 98.5%.

Probabilistic Graphical Models 1: Representation

2019. Stanford University. Grade: 94.5%.

Introduction to Machine Learning

2016. Higher School of Economics in cooperation with Yandex.

Grade 100%. Statement of Accomplishment.

numpy. pandas. scikit-learn. Decision trees. Linear and metric methods of classification. Gradient descent. Support vector machines. Logistic regression. Linear regression. PCA. SVM. Random forests. Neural nets.

R Programming

2016. Johns Hopkins University. Grade: 80.0%.

Practical Machine Learning

2016. Johns Hopkins University Grade: 97.6% (with Distinction).

The Data Scientist’s Toolbox

2016. Johns Hopkins University Grade: 100% (with Distinction).

Data Science and Machine Learning Essentials

2015. Microsoft. Grade: 77%. Verified Certificate of Achievement.

Machine Learning

2014. Stanford University. Grade 100%. Statement of Accomplishment. Linear Regression. Logistic Regression. Neural Networks. Support Vector Machines. K-means Clustering. Principal Components Analysis. Anomaly Detection. Collaborative Filtering.

Data Analysis and Statistical Inference

2014. Duke University. Grade 94%. Verified certificate with distinction. Probability and distributions. Confidence intervals. Hypothesis tests. Decision errors, significance, and confidence. Inference for numerical and categorical variables. Multiple linear regression.

Automata

2014. Stanford University. Grade: 83.7% (with Distinction). Statement of Accomplishment.