Meta-learning-based Data Feeding in Stock Market Prediction
Date:
Supervisor: Xiao Yang
- Developed and maintained the quant platform Qlib, a quantitative-research library for online trading.
- Focused on data feeding in stock market prediction. Proposed a meta-learning-based method to reweight samples. The meta-model learned to guide the retraining process of the base model by sample reweighting and aimed to improve the performance of the base model on unseen test data.
- Designed Meta-Controller, Reweighter frameworks in Qlib, and merged the meta-model into the frameworks.
- Finished an academic paper (page), it is accepted by AAAI 2022.