Efficient Delivery Policy to Minimize User Traffic Consumption in Guaranteed Advertising
Authors: Jia Zhang, Zheng Wang, Qian Li, Jialin Zhang, Yanyan Lan, Qiang Li, Xiaoming Sun
AAAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, the simulation shows that our method outperforms the traditional state-of-the-art methods. In this section, we perform some simulations of the flow based delivery policy and several other policies on different random graphs. |
| Researcher Affiliation | Academia | 1CAS Key Lab of Network Data Science and Technology, Institute of Computing Technology, Chinese Academy of Sciences, China. 2University of Chinese Academy of Sciences, China. 3Department of Computer Science, The University of Hong Kong, Hong Kong. |
| Pseudocode | Yes | Algorithm 1: Expected Flow Based Delivery Policy and Algorithm 2: GREEDY-DELIVERY-RULE |
| Open Source Code | No | The paper does not provide any links to source code or explicitly state that code is released. |
| Open Datasets | No | The paper describes generating synthetic data ('random graphs', 'random value rj') for its experiments, but does not use or provide concrete access information for a publicly available or open dataset. |
| Dataset Splits | No | The paper describes using '100 sampled user sequences' for evaluation in its simulation experiments but does not provide specific training/validation/test dataset splits in terms of percentages, sample counts, or citations to predefined splits. |
| Hardware Specification | Yes | Hardware A desktop with an Intel i5-4570 CPU @ 3.2GHZ and a 4GB DDR3 memory. |
| Software Dependencies | No | The paper does not list any specific software dependencies with version numbers. |
| Experiment Setup | Yes | Settings Restricted by the business model of GD, the size of demand-supply graph in real system is usually not large. Thus we conduct experiments on a random demand and supply graph with 500 ad campaigns and 1000 user types. Edges are generated uniformly and randomly while the average degree of user types are fixed. To generate the user types distribution D, we choose a random value rj > 0 for each uj, and set pj = rj 1000 l=1 rl . rj is chosen in two ways: rj is drawn uniformly from [0, 1] (we call this method Random-Normalization) or rj equals to 1 1000 +ε, where ε N(0, 1/60002) (we call this method Gauss-Perturbation). Wi is drawn uniformly from [50, 100]. |