Customer churn classification through a weights and structure determination neural network : доклад, тезисы доклада

Описание

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-II-2023); Krasnoyarsk; Krasnoyarsk

Год издания: 2024

Идентификатор DOI: 10.1051/itmconf/20245901004

Аннотация: In today's corporate world, acquiring and keeping clients are the most important priorities. Every business's market is expanding quickly, which is increasing the number of subscribers. Because neglect could result in a drop in profitability from a major standpoint, it has become imperative for service providers to limit churn rateПоказать полностьюs. These days, identifying which customers are most likely to leave a business requires a lot less work thanks to machine learning. Taking this into account, a novel weights and structure determination (WASD) neural network has been built to meet the aforementioned challenge of customer churn classification, as well as to handle its unique characteristics. Motivated by the observation that WASD neural networks outperform conventional back-propagation neural networks in terms of slow training speed and trapping in a local minimum, we enhance the WASD algorithm's learning process with a new activation function for best adapting to the customer churn model. Superior performance and flexibility to problems are demonstrated in an experimental investigation using a dataset from a telecommunications provider.

Ссылки на полный текст

Издание

Журнал: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-II-2023)

Номера страниц: 1004

Место издания: Krasnoyarsk

Персоны

  • Mourtas Spyridon D. (Laboratory "Hybrid Methods of Modelling and Optimization in Complex Systems", Siberian Federal University)

Вхождение в базы данных