Neural Networks for Tabular Data

Student: Bagiyan Nerses

Educational Programme: Data Science (Master)

Year of Graduation: 2021

In the modern world, neural networks have become one of the most important tools in numerous tasks: audio and video processing, machine translation, and recommendations. However, until now, the most common and frequently used tabular data. Until 2019, there were not any architectures that could perform better than the gradient boosting algorithm. However, since 2019, several algorithms have appeared that show comparable results with tabular data tasks. In this paper, we will explore the performance of tabular data algorithms, try to recreate the results that are given in the original works, and also we will try to improve existing models. At the end we will demonstrate how far we have advanced in terms of the quality of processing tabular data.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses