Seminars 2025
The Lab helds invited talks on NLP, Recommender Systems, Data Mining, and related topics twice a month. For more details see the Russian page.
Seminar Automatic Processing and Analysis of Texts & rdquo; dedicated to various processing tasks (tokenization, recovery segmentation, part-of-speech markup and syntactic parsing) and textual information parsing (extraction tasks information, construction and use of knowledge graphs, construction of question-answer systems, text classification, etc.).
Seminar on Genome-Wide Association Studies using Interpretable Machine Learning (GWAS&IML) (to be announced)
Online-Seminar "Forecasting Financial Flows Using Time Series Models and News Analytics"
Date: 2 nd October 18:00
Speaker: Ryabykh Alexey Gennadievich - Research Intern at the Laboratory for Social and Cognitive Informatics HSE SPb
Annotaion: Financial flow forecasting is a critical task for the banking sector, investment firms, and regulators. While modern machine learning methods, particularly global models, demonstrate high predictive accuracy, their application is limited by sensitivity to data quality, a lack of robust universal approaches for integrating diverse unstructured information (including financial news), and low forecast interpretability. This paper proposes effective procedures for time series preprocessing, methods for generating textual features to extract meaningful signals from the news flow and account for their impact on financial flow dynamics, approaches for building global models, and a framework for developing multi-modal models. These multi-modal models, based on topic modeling, integrate time series and textual data while preserving interpretability.
Have you spotted a typo?
Highlight it, click Ctrl+Enter and send us a message. Thank you for your help!
To be used only for spelling or punctuation mistakes.