Forecasting online advertising costs: interpretable deep learning of the competitive bidding landscape

• Autor(a) principal: Oldenburg, Fynn
• Data de Publicação: 2022
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10362/161184
• topic: Digital marketing; Online advertisement; Time series forecasting; Time series clustering; Deep learning; Temporal fusion transformer; Domínio/Área Científica::Ciências Sociais::Economia e Gestão

As advertisers increasingly shift their budgets toward digital advertising, forecasting ad vertising costs is essential for making budget plans to optimize marketing campaign re turns. In this paper, we perform a comprehensive study using a variety of time-series forecasting methods to predict daily average cost-per-click in the online advertising mar ket. We show that forecasting advertising costs would benefit from multivariate models using covariates from competitors’ cost-per-click development identified through time series clustering. We further interpret the results by analyzing feature importance and temporal attention. Finally, we show that our approach holds several advantages over, first, models that individual advertisers might build based on their own data, and second, existing tools from Google.