Online Advertising Revenue Forecasting: An Interpretable Deep Learning Approach
This work addresses a business issue for small and medium-sized publishers who rely on accurate revenue forecasts to manage website monetization strategies, though it is incremental in applying an existing method to a new domain-specific dataset.
The paper tackled the problem of forecasting online advertising revenues for publishers by using a Temporal Fusion Transformer model on a proprietary dataset of Google Adsense revenues, achieving superior performance over benchmark deep-learning time-series models across multiple time horizons.
Online advertising revenues account for an increasing share of publishers' revenue streams, especially for small and medium-sized publishers who depend on the advertisement networks of tech companies such as Google and Facebook. Thus publishers may benefit significantly from accurate online advertising revenue forecasts to better manage their website monetization strategies. However, publishers who only have access to their own revenue data lack a holistic view of the total ad market of publishers, which in turn limits their ability to generate insights into their own future online advertising revenues. To address this business issue, we leverage a proprietary database encompassing Google Adsense revenues from a large collection of publishers in diverse areas. We adopt the Temporal Fusion Transformer (TFT) model, a novel attention-based architecture to predict publishers' advertising revenues. We leverage multiple covariates, including not only the publisher's own characteristics but also other publishers' advertising revenues. Our prediction results outperform several benchmark deep-learning time-series forecast models over multiple time horizons. Moreover, we interpret the results by analyzing variable importance weights to identify significant features and self-attention weights to reveal persistent temporal patterns.