Configuring Qlib TRA with Alpha158 for CSI 300 Ranking
Summary
This configuration defines a Qlib experiment using Alpha158 features for the CSI 300 and the Shanghai 300 index as benchmark. It normalizes features with robust z-scores, fills missing values, filters a selected subset of columns, and applies cross-sectional rank normalization to labels. The prediction target is a forward close-to-close return, and the dataset uses sequences of 60 observations.
The model is a recurrent TRA setup using an LSTM architecture with attention, three latent states, and a router transport method. Training, validation, and test periods are separated, with the portfolio analysis covering the test period. The portfolio uses a top-k dropout strategy with specified transaction costs, price assumptions, and a limit threshold. These are experimental settings, not reported findings: the document supplies no metrics, comparison, or validation of predictive performance. Results would depend on the data and framework implementation, including processing and execution assumptions.
Key ideas
- The configuration applies Alpha158 features to a CSI 300 universe with a Shanghai 300 benchmark.
- Feature processing includes column filtering, robust normalization, and missing-value filling.
- Labels use a forward close-to-close return and are cross-sectionally rank-normalized.
- The model combines an LSTM with attention and a three-state TRA setup.
- Portfolio analysis uses top-k dropout and specified trading cost and price assumptions.
- No model performance results or comparisons are included.
Tags
Full text
# workflow_config_tra_Alpha158.yaml
```yaml
qlib_init:
provider_uri: "~/.qlib/qlib_data/cn_data"
region: cn
market: &market csi300
benchmark: &benchmark SH000300
data_handler_config: &data_handler_config
start_time: 2008-01-01
end_time: 2020-08-01
fit_start_time: 2008-01-01
fit_end_time: 2014-12-31
instruments: *market
infer_processors:
- class: FilterCol
kwargs:
fields_group: feature
col_list: ["RESI5", "WVMA5", "RSQR5", "KLEN", "RSQR10", "CORR5", "CORD5", "CORR10",
"ROC60", "RESI10", "VSTD5", "RSQR60", "CORR60", "WVMA60", "STD5",
"RSQR20", "CORD60", "CORD10", "CORR20", "KLOW"]
- class: RobustZScoreNorm
kwargs:
fields_group: feature
clip_outlier: true
- class: Fillna
kwargs:
fields_group: feature
learn_processors:
- class: CSRankNorm
kwargs:
fields_group: label
label: ["Ref($close, -2) / Ref($close, -1) - 1"]
num_states: &num_states 3
memory_mode: &memory_mode sample
tra_config: &tra_config
num_states: *num_states
rnn_arch: LSTM
hidden_size: 32
num_layers: 1
dropout: 0.0
tau: 1.0
src_info: LR_TPE
model_config: &model_config
input_size: 20
hidden_size: 64
num_layers: 2
rnn_arch: LSTM
use_attn: True
dropout: 0.0
port_analysis_config: &port_analysis_config
strategy:
class: TopkDropoutStrategy
module_path: qlib.contrib.strategy
kwargs:
signal: <PRED>
topk: 50
n_drop: 5
backtest:
start_time: 2017-01-01
end_time: 2020-08-01
account: 100000000
benchmark: *benchmark
exchange_kwargs:
limit_threshold: 0.095
deal_price: close
open_cost: 0.0005
close_cost: 0.0015
min_cost: 5
task:
model:
class: TRAModel
module_path: qlib.contrib.model.pytorch_tra
kwargs:
tra_config: *tra_config
model_config: *model_config
model_type: RNN
lr: 1e-3
n_epochs: 100
max_steps_per_epoch:
early_stop: 20
logdir: output/Alpha158
seed: 0
lamb: 1.0
rho: 0.99
alpha: 0.5
transport_method: router
memory_mode: *memory_mode
eval_train: False
eval_test: True
pretrain: True
init_state:
freeze_model: False
freeze_predictors: False
dataset:
class: MTSDatasetH
module_path: qlib.contrib.data.dataset
kwargs:
handler:
class: Alpha158
module_path: qlib.contrib.data.handler
kwargs: *data_handler_config
segments:
train: [2008-01-01, 2014-12-31]
valid: [2015-01-01, 2016-12-31]
test: [2017-01-01, 2020-08-01]
seq_len: 60
input_size:
num_states: *num_states
batch_size: 1024
n_samples:
memory_mode: *memory_mode
drop_last: True
record:
- class: SignalRecord
module_path: qlib.workflow.record_temp
kwargs:
model: <MODEL>
dataset: <DATASET>
- class: SigAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
ana_long_short: False
ann_scaler: 252
- class: PortAnaRecord
module_path: qlib.workflow.record_temp
kwargs:
config: *port_analysis_config
```Shown in full with attribution under the source's licence. Licence: MIT
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.