Research map / Time series / Causal and generative time series
Crowdfunding Dynamics Tracking: A Reinforcement Learning Approach
Jun Wang, Hefu Zhang, Qi Liu, Zhen Pan, Hanqing Tao
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 an options structure with two sub-policies to TC3 | TC3 · Indiegogo, test lengths 6–10 days | MAE, RMSE, and MAPE: 6-day MAE: 0.0234 -> 0.0201; RMSE: 0.0681 -> 0.0435; MAPE: 11.72% -> 9.05%; 7-day MAE: 0.0258 -> 0.0237; RMSE: 0.0771 -> | Improved |
| Use 1 option rather than 2 (ablation) | TC3-Options · Indiegogo 10-day | MAE, RMSE, and MAPE: MAE: 0.0201 -> 0.0234; RMSE: 0.0435 -> 0.0681; MAPE: 9.05% -> 11.72% | Hurt |
| Use 3 options rather than 2 (ablation) | TC3-Options · Indiegogo 10-day | MAE, RMSE, and MAPE: MAE: 0.0201 -> 0.0237; RMSE: 0.0435 -> 0.0468; MAPE: 9.05% -> 10.40% | Hurt |
| Use 4 options rather than 2 (ablation) | TC3-Options · Indiegogo 10-day | MAE, RMSE, and MAPE: MAE: 0.0201 -> 0.0246; RMSE: 0.0435 -> 0.0531; MAPE: 9.05% -> 11.52% | Hurt |
| Use 5 options rather than 2 (ablation) | TC3-Options · Indiegogo 10-day | MAE, RMSE, and MAPE: MAE: 0.0201 -> 0.0261; RMSE: 0.0435 -> 0.0582; MAPE: 9.05% -> 11.06% | Hurt |
Closest papers by meaning
- Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking (NeurIPS 2025 · similarity 0.80)
- InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma (ICLR 2025 · similarity 0.79)
- TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets (NeurIPS 2025 · similarity 0.79)
- MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model (ICLR 2025 · similarity 0.79)
- R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization (NeurIPS 2025 · similarity 0.78)
- EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies (NeurIPS 2026 · similarity 0.78)
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.
