Universal Trading for Order Execution with Oracle Policy Distillation

Authors: Yuchen Fang, Kan Ren, Weiqing Liu, Dong Zhou, Weinan Zhang, Jiang Bian, Yong Yu, Tie-Yan Liu107-115

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The extensive experiments have shown significant improvements of our method over various strong baselines, with reasonable trading actions. In this section, we present the details of the experiments.
Researcher Affiliation Collaboration 1Shanghai Jiao Tong University 2Microsoft Research
Pseudocode No No structured pseudocode or algorithm blocks were found.
Open Source Code Yes The open-source code and the supplementary are presented in this link3. https://seqml.github.io/opd/
Open Datasets No The paper mentions "historical transaction data of the stocks in the China A-shares market" and specifies its contents and time range, but does not provide any link, DOI, or formal citation for public access to this specific dataset. The provided URL is for code, not the dataset.
Dataset Splits Yes The dataset is divided into training, validation and test datasets according to the trading time. The detailed statistics are listed in Table 1. ... Training Validation Test instruments 3,566 855 855 order 1,654,385 35,543 33,176 Time 201701 201902 201903 201904 201905 201906
Hardware Specification No The paper does not provide any specific hardware details such as CPU/GPU models, memory specifications, or cloud instance types used for running experiments.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x) are explicitly mentioned in the paper.
Experiment Setup No The paper states, 'All these setting values are listed in the supplementary', but does not provide specific hyperparameter values or training configurations within the main text of the paper.