Bohdan Pavlyshenko

Position: Doctoral Candidate, System Design Department

Scientific degree: Candidate of Physical and Mathematical Sciences

Academic status: Associate Professor


Google Scholar profile:

LinkedIn profile:

Research interests

Scientific degree: Ph.D. in physics
Current Job Positions: Postdoc researcher at Ivan Franko Lviv National Univer- sity of Lviv (Ukraine), Data Scientist at SoftServe Inc.

I combines academic theories and practical approaches in the data science area. My current scientific interest lies in the following main areas:

• Predictive analytics

• Machine Learning

• Quantitative Linguistics, Natural Language Processing

• Social Network Mining

• Time Series Analytics

• Risk Assessment

In predictive analytics models, I combine machine learning and Bayesian infer- ence that is an effective approach for forecasting and risk assessment in business processes with non-Gaussian statistics. I work on the state-of-the-art predictive analytics solutions, taking part in Kaggle competitions where I have a Master de- gree and 7 medals for top positions in leaderboards, 3 of them are gold (highest rank was 89). I was a teammate of a team which won one Kaggle competition (“Grupo Bimbo Inventory Demand”) among nearly two thousand teams.


Totally I have more than 50 scientific publications. Here are some of data science related scientific papers:

  • Pavlyshenko, Bohdan. ”Clustering of Authors’ Texts of English Fiction in the Vector Space of Semantic Fields.” Cybernetics and Information Tech- nologies 14, no. 3 (2014): 25-36.
  • Genetic Optimization of Keyword Subsets in the Classification Analysis of Authorship of Texts // Journal of quantitative linguistics. – 2014. – Vol. 21, N4. – P. 341–349.
  • B.Pavlyshenko The Distribution of Semantic Fields in Author ́ıs Texts //Cy- bernetics and Information Technologies, DOI: 2016-0043, Volume 16, No 3, pp.195-204
  • Pavlyshenko, Bohdan M. ”Linear, machine learning and probabilistic ap- proaches for time series analysis.” In Data Stream Mining & Processing (DSMP), IEEE First International Conference on, pp. 377-381. IEEE, 2016.
  • Pavlyshenko, Bohdan. ”Machine learning, linear and Bayesian models for logistic regression in failure detection problems.” In Big Data (Big Data), 2016 IEEE International Conference on, pp. 2046-2050. IEEE, Washington D.C. 2016.
  • Pavlyshenko, B.M. Forecasting of Events by Tweets Data Mining. Elec- tronics and information technologies. 2018. Issue 10. P. 71–85.
  • Pavlyshenko, B.M. Can Twitter Predict Royal Baby’s Name ?. Electronics and information technologies. 2019. Issue 11. P. 52–60.
  • Pavlyshenko, B. (2018, August). Using Stacking Approaches for Machine Learning Models. In 2018 IEEE Second International Conference on Data Stream Mining & Processing (DSMP) (pp. 255-258). IEEE.
  • Pavlyshenko, B.M. Bitcoin Price Predictive Modeling Using Expert Cor- rection. 2019 XIth International Scientific and Practical Conference on Electronics and Information Technologies (ELIT), September 16 – 18, 2019 Lviv, Ukraine, pages: 163-167.
  • Pavlyshenko, B. M. Machine learning models for sales time series forecast- ing. Data 4, no. 1 (2019): 15.