Research map / Probabilistic and scientific modeling / Variational and generative sampling
Latent Dirichlet Allocation for Internet Price War
Chenchen Li, Xiang Yan, Xiaotie Deng, Yuan Qi, Wei Chu, Le Song, Junlong Qiao, Jianshan He, Junwu Xiong
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add inferred customer-preference and opponent-strategy features to DQN state (ablation) | DQN · Simulated price war against DQN | market share: 50.22% -> 65.16% | Improved |
| add inferred customer-preference features to DQN state (ablation) | DQN · Simulated price war against DQN | market share: 50.22% -> 55.84% | Improved |
| add inferred opponent-strategy features to DQN state (ablation) | DQN · Simulated price war against DQN | market share: 50.22% -> 56.72% | Improved |
| use dynamic programming with inferred preference and opponent-strategy distributions | Price War LDA framework · Simulated price war against Random Strategy | market share: 76.12% | Improved |
| use LDA-informed DQN rather than standard DQN | Price War LDA framework · Simulated price war against DQN | market share: 50.22% -> 65.16% | Improved |
| use LDA rather than Naive Bayes | O2O behavior prediction · O2O Dataset, test set | negative log likelihood: 494.93 -> 401.97 | Improved |
| infer opponent strategy with LDA rather than use the overall average distribution | O2O strategy estimation · O2O Dataset, strategy groups | Wasserstein distance: 0.13105 -> 0.12303 | Improved |
| use LDA rather than Neural Network | Financial marketing behavior prediction · Financial marketing dataset, test set | negative log likelihood: 449.52 -> 259.60 | Improved |
| use Price War LDA-informed DRL rather than Random Strategy | Financial marketing · Financial marketing, two weeks after awards | product usage rate: 2.1697% -> 2.8053%; 29.29% | Improved |
| use Price War LDA-informed DRL rather than standard DQN | Financial marketing · Financial marketing, two weeks after awards | product usage rate: 2.4966% -> 2.8053% | Improved |
Closest papers by meaning
- Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces (ICLR 2024 · similarity 0.85)
- Online Learning in Betting Markets: Profit versus Prediction (ICML 2024 · similarity 0.85)
- Multi-Sender Persuasion: A Computational Perspective (ICML 2024 · similarity 0.84)
- A Parametric Contextual Online Learning Theory of Brokerage (ICML 2025 · similarity 0.84)
- Interference Among First-Price Pacing Equilibria: A Bias and Variance Analysis (ICLR 2025 · similarity 0.84)
- Homogeneous Algorithms Can Reduce Competition in Personalized Pricing (NeurIPS 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
