Efficient Optimal Selection for Composited Advertising Creatives with Tree Structure
Authors: Jin Chen, Tiezheng Ge, Gangwei Jiang, Zhiqiang Zhang, Defu Lian, Kai Zheng3967-3975
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We finally evaluate the proposed algorithm on the synthetic dataset and the real-world dataset. The results show that our approach can outperform competing baselines in terms of convergence rate and overall CTR. |
| Researcher Affiliation | Collaboration | Jin Chen 1, Tiezheng Ge2, Gangwei Jiang 3, Zhiqiang Zhang2, Defu Lian 3, Kai Zheng1 1University of Electronic Science and Technology of China 2Alibaba Group 3University of Science and Technology of China |
| Pseudocode | Yes | Algorithm 1: Dynamic Programming for Ads Selection; Algorithm 2: AES (Adaptive and Efficient ad creative Selection framework) |
| Open Source Code | Yes | https://github.com/alimama-creative/AES-Adaptive-and Efficient-ad-creative-Selection |
| Open Datasets | No | The paper uses a 'synthetic dataset' and a 'real-world dataset' but does not provide concrete access information (link, DOI, repository, or formal citation with author/year for public availability) for either dataset. |
| Dataset Splits | No | The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, or testing. |
| Hardware Specification | Yes | Our experiments are conducted in a Linux system with 256G memory and CPU E5-2682. |
| Software Dependencies | No | The paper does not provide specific ancillary software details, such as library names with version numbers, needed to replicate the experiment. |
| Experiment Setup | Yes | We set ϵ = 0.1. ... and λ is set 0.03. ... We set the number of iterations S = 4 and K = 3 for hill climbing as mentioned in (Hill et al. 2017). |