本仓库是论文《Real-time Bidding Strategy in Display Advertising: An Empirical Analysis》的代码。
我们使用基准数据集iPinYou。数据下载以及标准化请参见 make-ipinyou-data 。
数据标准化后，将每个广告活动（如 1458 ）的 train.log.txt 和 text.log.txt 文件复制到 RLBid_EA/data/ipinyou/1458 以便进一步使用。
在训练出价策略前，首先需预测每个广告曝光的点击率。我们在 RLBid_EA/ctr/models 提供了4个数据集的FM预训练模型参数，你可以配合 RLBid_EA/ctr/generate_pctr.py 使用。
你当然也能够自己训练一个CTR预测器。RLBid_EA/ctr/model.py 实现了9个经典的点击率预测模型。
| 模型 | 论文 | 链接 |
|---|---|---|
| LR | Predicting clicks: estimating the click-through rate for new ads | [paper] |
| FM | Factorization machines | [paper] |
| FFM | Field-aware factorization machines for CTR prediction | [paper] |
| W&D | Wide & deep learning for recommender systems | [paper] |
| PNN | Product-based neural networks for user response prediction | [paper] |
| DeepFM | DeepFM: a factorization-machine based neural network for CTR prediction | [paper] |
| FNN | Deep learning over multi-field categorical data | [paper] |
| DCN | Deep & cross network for ad click predictions | [paper] |
| AFM | Attentional factorization machines: Learning the weight of feature interactions via attention networks | [paper] |
具体的使用方法请参见 README
本仓库实现了2个静态出价策略和3个基于强化学习的动态出价策略。
| 模型 | 论文 | 链接 |
|---|---|---|
| LIN | Bid optimizing and inventory scoring in targeted online advertising | [paper] |
| ORTB | Optimal real-time bidding for display advertising | [paper] [code] |
| RLB | Real-time bidding by reinforcement learning in display advertising | [paper] [code] |
| DRLB | Budget constrained bidding by model-free reinforcement learning in display advertising | [paper] |
| FAB | A dynamic bidding strategy based on model-free reinforcement learning in display advertising | [paper] [code] |
具体的使用方法请参见每个文件夹下的README
本项目采用 Apache License 2.0
- @JiaXingBinggan 贡献了本仓库的CTR预测模型代码