Bayesian Deep Learning Meets Self-Attention: A Risk-Aware Approach to Advertisement Optimization
Open Access
- 15 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 86413-86429
Abstract
In the highly competitive landscape of e-commerce advertising, maximizing Return on Advertising Spend (ROAS) is critical, yet remains inherently uncertain due to auction-based bidding dynamics and fluctuating market conditions. Traditional deterministic models fail to capture this uncertainty, necessitating a probabilistic approach that balances predictive accuracy with interpretability. To address this challenge, the paper proposes a novel Hierarchical Bayesian Deep Learning framework that integrates a Bayesian Belief Network (BBN) for structured probabilistic reasoning and a Mixture Density Network (MDN) for full distributional modeling of ROAS. The BBN models dependencies among campaign variables, offering interpretable insights, while the hierarchical deep learning architecture overcomes scalability limitations in high-dimensional settings through self-attention mechanisms. Experiments demonstrate up to 22.8% lower RMSE and 27.4% better Negative Log Likelihood (NLL) and up to 31.2% lower Kullback-Leibler divergence (KLD) than state-of-the-art methods (DeepAR, Prophet, NGBoost), achieving an R² of 98% with an inference speed of 5.2 ms per campaign, making real-time bidding feasible. Ablation studies confirm that attention-driven feature selection and calibrated uncertainty quantification significantly enhance both predictive performance and explainability, identifying key drivers of campaign success. By providing precise, uncertainty-aware, and explainable predictions, this approach enables adaptive bidding strategies, optimized budget allocation, and risk management, setting a new benchmark for intelligent decision-making in digital advertising.Keywords
Funding Information
- M/s. CommerceIQ and rBoomerang Retail Commerce Technologies India Private Ltd
This publication has 40 references indexed in Scilit:
- Bid Landscape Forecasting and Cold Start Problem With TransformersIEEE Access, 2024
- Extreme gradient boosting trees with efficient Bayesian optimization for profit-driven customer churn predictionTechnological Forecasting and Social Change, 2023
- Multi-Objective Actor-Critics for Real-Time Bidding in Display Advertising2023
- Probabilistic deep learning for real-time large deformation simulationsComputer Methods in Applied Mechanics and Engineering, 2022
- Session interest model for CTR prediction based on self-attention mechanismScientific Reports, 2022
- Long short term memory–convolutional neural network based deep hybrid approach for solar irradiance forecastingApplied Energy, 2021
- DeepAR: Probabilistic forecasting with autoregressive recurrent networksInternational Journal of Forecasting, 2020
- Forecasting at ScaleThe American Statistician, 2018
- Deep Learning Applications in Medical Image AnalysisIEEE Access, 2017
- Computational Intelligence and Financial Markets: A Survey and Future DirectionsExpert Systems with Applications, 2016