From 6e3ffa3724cdb2a3c79aab947004a42fadf3656d Mon Sep 17 00:00:00 2001 From: Wendi Li Date: Mon, 2 Jan 2023 10:15:50 -0600 Subject: [PATCH] [DDG-DA] Update crowd-sourced data results (#1405) * [DDG-DA] Update crowd-sourced data experiments * Remove internal data version * Modify README --- examples/benchmarks_dynamic/DDG-DA/workflow.py | 2 +- examples/benchmarks_dynamic/README.md | 16 +++++++++++----- 2 files changed, 12 insertions(+), 6 deletions(-) diff --git a/examples/benchmarks_dynamic/DDG-DA/workflow.py b/examples/benchmarks_dynamic/DDG-DA/workflow.py index 2d7427cfdb..48ea9bdb3e 100644 --- a/examples/benchmarks_dynamic/DDG-DA/workflow.py +++ b/examples/benchmarks_dynamic/DDG-DA/workflow.py @@ -170,7 +170,7 @@ def train_meta_model(self): # 3) train and logging meta model with R.start(experiment_name=self.meta_exp_name): R.log_params(**kwargs) - mm = MetaModelDS(step=self.step, hist_step_n=kwargs["hist_step_n"], lr=0.001, max_epoch=200, seed=43) + mm = MetaModelDS(step=self.step, hist_step_n=kwargs["hist_step_n"], lr=0.001, max_epoch=100, seed=43) mm.fit(md) R.save_objects(model=mm) diff --git a/examples/benchmarks_dynamic/README.md b/examples/benchmarks_dynamic/README.md index e6d09902a4..261fcc0356 100644 --- a/examples/benchmarks_dynamic/README.md +++ b/examples/benchmarks_dynamic/README.md @@ -4,15 +4,21 @@ So adapting the forecasting models/strategies to market dynamics is very importa The table below shows the performances of different solutions on different forecasting models. -## Alpha158 dataset +## Alpha158 Dataset +Here is the [crowd sourced version of qlib data](data_collector/crowd_source/README.md): https://github.com/chenditc/investment_data/releases +```bash +wget https://github.com/chenditc/investment_data/releases/download/20220720/qlib_bin.tar.gz +tar -zxvf qlib_bin.tar.gz -C ~/.qlib/qlib_data/cn_data --strip-components=2 +``` | Model Name | Dataset | IC | ICIR | Rank IC | Rank ICIR | Annualized Return | Information Ratio | Max Drawdown | |------------------|---------|----|------|---------|-----------|-------------------|-------------------|--------------| -| RR[Linear] |Alpha158 |0.088|0.570|0.102 |0.622 |0.077 |1.175 |-0.086 | -| DDG-DA[Linear] |Alpha158 |0.093|0.622|0.106 |0.670 |0.085 |1.213 |-0.093 | -| RR[LightGBM] |Alpha158 |0.079|0.566|0.088 |0.592 |0.075 |1.226 |-0.096 | -| DDG-DA[LightGBM] |Alpha158 |0.084|0.639|0.093 |0.664 |0.099 |1.442 |-0.071 | +| RR[Linear] |Alpha158 |0.089|0.577|0.102 |0.627 |0.093 |1.458 |-0.073 | +| DDG-DA[Linear] |Alpha158 |0.096|0.636|0.107 |0.677 |0.067 |0.996 |-0.091 | +| RR[LightGBM] |Alpha158 |0.082|0.589|0.091 |0.626 |0.077 |1.320 |-0.091 | +| DDG-DA[LightGBM] |Alpha158 |0.085|0.658|0.094 |0.686 |0.115 |1.792 |-0.068 | - The label horizon of the `Alpha158` dataset is set to 20. - The rolling time intervals are set to 20 trading days. - The test rolling periods are from January 2017 to August 2020. +- The results are based on the crowd-sourced version. The Yahoo version of qlib data does not contain `VWAP`, so all related factors are missing and filled with 0, which leads to a rank-deficient matrix (a matrix does not have full rank) and makes lower-level optimization of DDG-DA can not be solved.