Exploring Autoencoder-based Representations for Tabular Data Classification
Il’murat TokhtakhunovDepartment of Mathematical and Computer Modelling , International Information Technology University , 34/1 Manas street , Almaty , 05000 , KazakhstanMarat NurtasDepartment of Mathematical and Computer Modelling , International Information Technology University , 34/1 Manas street , Almaty , 05000 , KazakhstanAlexander NeftissovScience Innovation Center Industry 4 Sharofiddin PirnaevDepartment of Engineering Technological Machines , Tashkent State Transport University , 1 Temiryolchilar street , Mirabad district , Tashkent , 100167 , UzbekistanIlyas KazambayevAcademy of Physical Education and Mass Sports , Mangilik El B2.2 , Astana , 010000 , KazakhstanLalita KirichenkoAcademy of Physical Education and Mass Sports , Mangilik El B2.2 , Astana , 010000 , Kazakhstan
2025en
Ochiq kirishOlmos
ABI
Annotatsiya
Autoencoders are evaluated as a means of constructing compact and informative vector representations for classification tasks involving high-dimensional tabular data.The methodology addresses the limitations of traditional models that rely on manual feature engineering and taskspecific training.Emphasis is placed on building a generalized look-alike model for targeted advertising, using embeddings derived from subscriber-related entities.The approach is assessed on a real-world telecommunications dataset comprising subscriber demographics, devices, tariffs, and network characteristics.Experimental results demonstrate that embeddings produced by
Hali tarjima qilinmagan
Identifikatorlar
Iqtiboslar va manbalar
0 ta iqtibos0 ta foydalanilgan manba