We investigate a class of emerging online marketing challenges in social networks; macro behavioral targeting (MBT) is introduced as non-personalized broadcasting efforts to massive populations. We propose a new probabilistic graphical model for MBT. Further, a linear-time approximation method is proposed to circumvent an intractable parametric representation of user behaviors. We compare the proposed model with the existing state-of-the-art method on real datasets from social networks. Our model outperforms in all categories by comfortable margins.
If you find the code in this respository useful for your research, please cite our paper:
@inproceedings{xie2013graphical,
title={Graphical modeling of macro behavioral targeting in social networks},
author={Xie, Yusheng and Chen, Zhengzhang and Zhang, Kunpeng and Patwary, Md Mostofa Ali and Cheng, Yu and Liu, Haotian and Agrawal, Ankit and Choudhary, Alok},
booktitle={Proceedings of the 2013 SIAM International Conference on Data Mining},
pages={740--748},
year={2013},
organization={SIAM}
}
- Target audience: Brand and social media marketers and researchers
- Problem: Marketers spend millions every month to acquire Facebook fans
- We spent $30M and acquired 20M FB fans. Now what? – a major US retailer
- Research question: How to optimally engage one’s fans so that they stay active and retain their value to the brand?
- FB user => Fan => Engaged Fan => Customer
- Facebook Engagement Model
- Three major components in MBT model
- User parametrization
- Features
- Prediction performance
- Optimization terms
