Control of informational impacts on project management

Teslia, Yurii; Khlevnyi, Andrii; Khlevna, Iulia; Gerasymenko, Svetlana

doi:10.1109/dsmp.2016.7583584

Cited by 13 publications

(1 citation statement)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To expand the analysis, numerous studies have explored various machine learning algo rhythms and their potential for outflow modeling. Since predicting whether a client will be lost is not a binary classification problem, several models have been tested, such as logistic regression [23,32], decision trees [29,31], random forest, supporting vector machines, and neural networks [23].…”

Section: Analysis Of Methods For Predicting Interactions In Startupsmentioning

confidence: 99%

Predicting Customer Churn Using Machine Learning in IT Startups

Morozov

Mezentseva

Kolomiiets

et al. 2021

Lecture Notes in Computational Intelligence and Decision Making

View full text Add to dashboard Cite

This work is devoted to the consideration of the issues of increasing the development of start-up projects with using modern methods of artificial intelligence. As a rule, such projects are based on innovations and their implementation requires registration as independent enterprises. Operating in market conditions, most IT companies are forced to develop new innovative ideas and present them in the form of startups At the same time, small and medium-sized businesses interact with many external independent potential customers. Such users of information systems may subsequently become clients of such enterprises. The growth and development of these SaaS enterprises relies heavily on the average customer, which is the topic of this article, with the goal of reducing customer churn. The direction of such research is addressed in many of the rules of thumb for SaaS metrics. In these conditions, it is important to take into account the completeness of the functional interaction of SaaS customers, the authors proposed a hypothesis on the possibility of using intelligent methods for predicting customer churn using deep learning neural networks. At the same time, the needs of the stakeholders of such projects should be taken into account, the satisfaction of which occurs when interacting with an innovative IT product. To describe the interactions, the authors consider mathematical models, and also propose modeling methods. To conduct chain training, Python functionality is used, with the processing of user activity datasets. In this paper, a section of the conclusion is proposed in which the results obtained are discussed and evaluated.

show abstract

Section: Analysis Of Methods For Predicting Interactions In Startupsmentioning

confidence: 99%